Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
10 results
Search Results
Item Laboratory Evaluation of SMA Mixtures Made with Polymer-Modified Bitumen and Stabilizing Additives(American Society of Civil Engineers (ASCE) onlinejls@asce.org, 2019) Shiva Kumar, G.; Ravi Shankar, A.U.; Ravi Teja, B.V.S.Stone matrix asphalt (SMA) is a gap-graded mixture that consists of two parts, a high concentration coarse aggregate skeleton and a high binder content mortar. The coarse aggregate skeleton provides the mixture with stone-on-stone contact, giving it strength, while the high binder content mortar adds durability. The mortar is typically composed of fine aggregate, mineral filler, asphalt binder, and a stabilizing additive. A stabilizing additive such as natural fibers, mineral fibers, or polymers is added to SMA mixtures to prevent draindown. In addition, it has the potential of reinforcing and improving the tensile strength and cohesion of SMA mixtures. In this study, banana fiber (BF) and pelletized fiber (VP) are used as stabilizing additives to prepare SMA mixtures with conventional viscosity-graded (VG) 30 bitumen. Mixtures were prepared with different levels BF and VP content, and another mixture without any stabilizers was also prepared using polymer-modified bitumen (PMB). Superpave mix design, draindown, fatigue, rutting, workability, and moisture-induced damage properties were evaluated. Results indicated that addition of natural and pelletized fiber controls binder draindown and improves resistance to rutting, fatigue, and moisture-induced damage of SMA mixture. Further, polymer-modified SMA mixtures take less energy for densification compared to SMA mixtures with natural and pelletized fiber. Results also showed that even though polymer-modified SMA mixtures performed better, SMA mixtures with pelletized fiber provided comparable results. © 2019 American Society of Civil Engineers.Item Musculoskeletal Disorders Among Dozer Operators Exposed to Whole-Body Vibration in Indian Surface Coal Mines(Springer, 2020) Jeripotula, S.K.; Mangalpady, A.; Raj, G.R.Dozer operators are frequently exposed to whole-body vibration (WBV) during the execution of their work. Occupational exposure to WBV in Indian surface coal mines was evaluated by measuring vibration intensity and duration of exposure. A triaxial accelerometer was placed on the operator seat surface for taking the readings. Based on frequency-weighted root mean square acceleration equivalent to 8-hr shift duration, i.e., (A(8)) all dozer operators have exceeded an Exposure Action Value (EAV) of 0.5 m/s2, and 90% of dozers did not exceed Exposure Limit Value (ELV) of 1.15 m/s2. Based on Vibration Dose Value (VDV (8)), all dozer operators have exceeded Exposure Limit Value (EAV) of 9.1 m/s1.75, but no dozer operators have exceeded Exposure Limit Value (ELV) of 21 m/s1.75. Further, an epidemiological study was performed for identifying the extent of musculoskeletal disorders (MSDs) among dozer operators. For the detailed study, 42 dozer operators and 22 controls were selected from 2 surface coal mines. The control group was not exposed to WBV. It was seen from the cross-sectional study that pain in the lower back was predominantly higher (83.33%) in the exposed group when compared with the control group (31.81%). Likewise, pain in the neck (47.61%), shoulder (42.85%), knees (42.85%), and ankle (11.90%) was higher in the exposed group than that of the control group (22.71%, 0%, 45.45%, and 4.54%). A significant observation among the exposed group was that there was degradation in the quality of life. The outcome of the study would assist in monitoring and mitigation of machinery-induced vibration diseases (MIVD) in India and generally applicable to most of the mechanized mines as well. However, comprehensive studies are still needed to enunciate the magnitude extent. © 2020, Society for Mining, Metallurgy & Exploration Inc.Item Ergonomic Assessment of Musculoskeletal Disorders Among Surface Mine Workers in India(Springer Science and Business Media Deutschland GmbH, 2021) Jeripotula, S.K.; Mangalpady, M.; Raj, G.R.Injuries due to work-related musculoskeletal disorders (WMSDs) are not uncommon in heavy industry like mining. Researchers acknowledged that occupational exposure to ergonomic risk factors is the chief causative factor in the development of WMSDs. The aim of this study was to perform an ergonomic assessment of musculoskeletal disorders among surface mine workers in India. Standardized Nordic Questionnaire was used to collect subjective response from 500 workers. A stratified random sampling method according to surface mining work activity type was used to obtain the sample. Data was collected by means of a structured questionnaire, and the Statistical Package for Social Sciences (SPSS) was used to analyze data using descriptive and inferential statistical methods. A response rate of 85% was obtained out of 500 targeted groups. The WMSDs prevalence for the 12-month period was estimated to be 44.23%. The mean and standard deviation of workers’ age were 41.31and 8.927, respectively. The study has shown that the operators of dumpers, dozers, and graders along with electricians were found to be the most susceptible to develop WMSD problems. Among the most affected body parts, back disorder reported the highest. Further, it was found that working with static posture over the longer duration has a significant association with the lower back disorder (with p = 0.020) and bouncing and jarring has also significantly associated with the lower back disorder (with p = 0.023). Similarly, a significant association was found between repetitive work and neck pain (with p = 0.016). The study depicted a significant association between ergonomic hazards and WMSDs, like working with prolonged static posture, bouncing and jarring, and repetitive work. © 2020, Society for Mining, Metallurgy & Exploration Inc.Item Human identification system using 3D skeleton-based gait features and LSTM model(Academic Press Inc., 2022) Rashmi, M.; Guddeti, R.M.R.Vision-based gait emerged as the preferred biometric in smart surveillance systems due to its unobtrusive nature. Recent advancements in low-cost depth sensors resulted in numerous 3D skeleton-based gait analysis techniques. For spatial–temporal analysis, existing state-of-the-art algorithms use frame-level information as the timestamp. This paper proposes gait event-level spatial–temporal features and LSTM-based deep learning model that treats each gait event as a timestamp to identify individuals from walking patterns observed in single and multi-view scenarios. On four publicly available datasets, the proposed system stands superior to state-of-the-art approaches utilizing a variety of conventional benchmark protocols. The proposed system achieved a recognition rate of greater than 99% in low-level ranks during the CMC test, making it suitable for practical applications. The statistical study of gait event-level features demonstrated retrieved features’ discriminating capacity in classification. Additionally, the ANOVA test performed on findings from K folds demonstrated the proposed system's significance in human identification. © 2021 Elsevier Inc.Item Musculoskeletal Disorder Risk in the Upper Extremities of Mobile Mining Equipment Operators Exposed to Hand-Transmitted Vibrations in Underground Metal Mines: a Case–Control Study(Springer Science and Business Media Deutschland GmbH, 2022) Sridhar, S.; Raj, M.G.; Mangalpady, M.Hand-transmitted vibration (HTV) exposure is associated with various health risks for operators of mobile mining equipment (MME). The case–control research was conducted to determine the musculoskeletal disorder (MSD) risks associated with exposure to HTVs in the exposed (case) and non-exposed (control) groups. HTV readings were measured at the interface between the hand and the steering device using the SV 105B triaxial hand accelerometer connected to the SV106 human vibration analyzer involving 40 MME operators in accordance with ISO 5349:2001 guidelines. A questionnaire survey was also carried out among both the study groups using Cornell Musculoskeletal Discomfort Questionnaire. The European Union's 2002/44/E.C. was used to assess the health risks posed to the MME operators. Twenty-eight out of the 40 MMEs were generating HTVs exceeding the stipulated daily limits of vibration, putting 70% of the operators at increased risk for developing MSDs. The case group was found to have an elevated risk of exposure with odds ratio (OR) 7.56 (95% confidence interval (CI), 1.159, 49.39) and OR 12.80 (95% CI, 2.436, 67.285) times more likely than the control group to suffer discomfort in the left shoulder and left wrist, respectively, indicating increased risk of exposure to HTV. Additionally, cases had elevated risk associated with exposure to tobacco, OR 9.35(95% CI, 1.856, 47.129) compared to those who did not use tobacco. MSDs were more prevalent in the case group compared to the control group. This observation was validated by the field investigations and the responses of MME operators to the questionnaires. © 2022, Society for Mining, Metallurgy & Exploration Inc.Item Deep learning-based multi-view 3D-human action recognition using skeleton and depth data(Springer, 2023) Ghosh, S.K.; Rashmi, M.; Mohan, B.R.; Guddeti, R.M.R.Human Action Recognition (HAR) is a fundamental challenge that smart surveillance systems must overcome. With the rising affordability of capturing human actions with more advanced depth cameras, HAR has garnered increased interest over the years, however the majority of these efforts have been on single-view HAR. Recognizing human actions from arbitrary viewpoints is more challenging, as the same action is observed differently from different angles. This paper proposes a multi-stream Convolutional Neural Network (CNN) model for multi-view HAR using depth and skeleton data. We also propose a novel and efficient depth descriptor, Edge Detected-Motion History Image (ED-MHI), based on Canny Edge Detection and Motion History Image. Also, the proposed skeleton descriptor, Motion and Orientation of Joints (MOJ), represent the appropriate action by using joint motion and orientation. Experimental results on two datasets of human actions: NUCLA Multiview Action3D and NTU RGB-D using a Cross-subject evaluation protocol demonstrated that the proposed system exhibits the superior performance as compared to the state-of-the-art works with 93.87% and 85.61% accuracy, respectively. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item Fuzzy Logic-Based Rapid Upper Limb Assessment: A Novel Approach to Evaluate the Postural Risk of Dumper Operators(Springer, 2023) Kar, M.B.; Mangalpady, M.; Kunar, B.M.It is proved that the accuracy of the standard Rapid Upper Limb Assessment (RULA) method for evaluating the risk of work-related musculoskeletal disorders (WRMSDs) is often poor. In this paper, a fuzzy logic-based RULA system was developed to address this issue using the MATLAB software package. To evaluate the developed system, 15 dumper operators working in the surface iron ore mine were randomly selected. Video footage of their driving postures was recorded while they were performing different job cycles, such as loading, full-load travel, unloading, and empty travel. The video footage was examined to identify the most frequent driving postures. From this posture, the range of motion of both the axial and appendicular body parts was measured. The measured data were used as input parameter for the fuzzy model to calculate the fuzzy RULA score. The result revealed that 20% of the driving postures adopted by the dumper operators correspond to the medium risk of WRMSDs. Furthermore, the interquartile range of the fuzzy RULA score during dynamic operations was found to be small. This indicates that the fuzzy RULA score remained consistent throughout the dynamic operations. In contrast, the interquartile range exhibited large magnitude in the static operations, thus indicating a greater level of variation in fuzzy RULA score. The correlation test and Bland–Altman analysis were performed to compare the standard and fuzzy RULA scores. This analysis proved that the fuzzy logic-based method is a reliable alternative to the standard method for assessing RULA scores among dumper operators. © 2023, The Institution of Engineers (India).Item Exploiting skeleton-based gait events with attention-guided residual deep learning model for human identification(Springer, 2023) Rashmi, M.; Guddeti, R.M.R.Human identification using unobtrusive visual features is a daunting task in smart environments. Gait is among adequate biometric features when the camera cannot correctly capture the human face due to environmental factors. In recent years, gait-based human identification using skeleton data has been intensively studied using a variety of feature extractors and more sophisticated deep learning models. Although skeleton data is susceptible to changes in covariate variables, resulting in noisy data, most existing algorithms employ a single feature extraction technique for all frames to generate frame-level feature maps. This results in degraded performance and additional features, necessitating increased computing power. This paper proposes a robust feature extractor that extracts a quantitative summary of gait event-specific information, thereby reducing the total number of features throughout the gait cycle. In addition, a novel Attention-guided LSTM-based deep learning model with residual connections is proposed to learn the extracted features for gait recognition. The proposed approach outperforms the state-of-the-art works on five publicly available datasets on various benchmark evaluation protocols and metrics. Further, the CMC test revealed that the proposed model obtained higher than 97% Accuracy in lower-level ranks on these datasets. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item Human action recognition using multi-stream attention-based deep networks with heterogeneous data from overlapping sub-actions(Springer Science and Business Media Deutschland GmbH, 2024) Rashmi, M.; Guddeti, R.M.R.Vision-based Human Action Recognition is difficult owing to the variations in the same action performed by various people, the temporal variations in actions, and the difference in viewing angles. Researchers have recently adopted multi-modal visual data fusion strategies to address the limitations of single-modality methodologies. Many researchers strive to produce more discriminative features because most existing techniques’ success relies on feature representation in the data modality under consideration. Human action consists of several sub-actions whose duration vary between individuals. This paper proposes a multifarious learning framework employing action data in depth and skeleton formats. Firstly, a novel action representation named Multiple Sub-action Enhanced Depth Motion Map (MS-EDMM), integrating depth features from overlapping sub-actions, is proposed. Secondly, an efficient method is introduced for extracting spatio-temporal features from skeleton data. This is achieved by dividing the skeleton sequence into sub-actions and summarizing skeleton joint information for five distinct human body regions. Next, a multi-stream deep learning model with Attention-guided CNN and residual LSTM is proposed for classification, followed by several score fusion operations to reap the benefits of streams trained with multiple data types. The proposed method demonstrated a superior performance of 1.62% over an existing method that utilized skeleton and depth data, achieving an accuracy 89.76% on a single-view UTD-MHAD dataset. Furthermore, on the multi-view NTU RGB+D dataset demonstrated encouraging performance with an accuracy of 89.75% in cross-view and 83.8% in cross-subject evaluations. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.Item CAEB7-UNet: An Attention-Based Deep Learning Framework for Automated Segmentation of C-Spine Vertebrae in CT Images(Institute of Electrical and Electronics Engineers Inc., 2025) Pandey, A.K.; Senapati, K.; Pateel, G.P.Accurate segmentation of vertebrae in computed tomography (CT) images possess serious challenges due to the irregular vertebral boundaries, low contrast and brightness, and noise in CT scans. This study presents a novel channel attention-based EfficientNetB7-UNet (CAEB7-UNet) method to address this complex task effectively. The proposed model introduces an upgraded ReLU-based channel attention module (CAM) in the skip connection which restrains the nonessential attributes by suppressing them and accentuates the relevant features by emphasizing them to boost the overall segmentation performance. In this work, an improved EfficientNetB7 is employed as the encoder for feature extraction, the fusion of local and global features is enhanced through the upgraded CAM in skip connection, and the up-sampling is performed in the decoder. Further, the model is optimized by incorporating hyperparameter optimization, specifically, hybrid learning rate scheduler strategies, along with the AdamW optimizer and custom data augmentation. A total of 34,782 CT images obtained from the RSNA-2022 cervical spine fracture detection challenge is utilized in this study. The proposed model achieves outstanding performance, yielding a dice score index (DSI) of 96.14% and mean intersection over union (mIoU) of 91.46%. Moreover, a comparative performance analysis of CAEB7-UNet with two state-of-the-art models is carried out on the same dataset. Our approach outperforms both the models, with the best one by 8.1%, 6.73%, 12.7%, and 11.98% in terms of DSI, mIoU, precision, and F1-score respectively. Additionally, it requires merely 0.38 seconds to generate the segmentation mask of a single slice of a CT scan. © 2013 IEEE.