arXiv subjects

Akshay Deepak

Publications and source records attributed to Akshay Deepak.

12 recordsLinked to original sources

arXiv2026

Robust Visual SLAM for UAV Navigation in GPS-Denied and Degraded Environments: A Multi-Paradigm Evaluation and Deployment Study

Reliable localization in GPS-denied, visually degraded environments is critical for autonomous UAV opera- tions. This paper presents a systematic comparative evaluation of five V-SLAM systems ORB-SLAM3, DPVO, DROID-SLAM, DUSt3R, and MASt3R spanning classical, deep learning, recurrent, and Vision Transformer (ViT) paradigms. Experiments are conducted on curated sequences from four public benchmarks (TUM RGB-D, EuRoC MAV, UMA-VI, SubT-MRS) and a custom monocular indoor dataset under five controlled degradation conditions (normal, low light, dust haze, motion blur, and combined), with sub-millimeter Vicon ground truth. Results show that ORB-SLAM3 fails critically under severe degradation (62.4% overall TSR; 0% under dense haze), while learning-based methods remain robust: MASt3R achieves the lowest degraded ATE (0.027 m) and DUSt3R the highest tracking success (96.5%). DPVO offers the best efficiency robustness trade-off (18.6 FPS, 3.1 GB GPU memory, 86.1% TSR), making it the preferred choice for memory-constrained embedded platforms. Embedded deployment analysis across NVIDIA Jetson platforms provides actionable guidelines for SLAM selection under SWaP-constrained UAV scenarios.

cs.RO↗

arXiv2022

{\lambda}-Scaled-Attention: A Novel Fast Attention Mechanism for Efficient Modeling of Protein Sequences

Attention-based deep networks have been successfully applied on textual data in the field of NLP. However, their application on protein sequences poses additional challenges due to the weak semantics of the protein words, unlike the plain text words. These unexplored challenges faced by the standard attention technique include (i) vanishing attention score problem and (ii) high variations in the attention distribution. In this regard, we introduce a novel {\lambda}-scaled attention technique for fast and efficient modeling of the protein sequences that addresses both the above problems. This is used to develop the {\lambda}-scaled attention network and is evaluated for the task of protein function prediction implemented at the protein sub-sequence level. Experiments on the datasets for biological process (BP) and molecular function (MF) showed significant improvements in the F1 score values for the proposed {\lambda}-scaled attention technique over its counterpart approach based on the standard attention technique (+2.01% for BP and +4.67% for MF) and state-of-the-art ProtVecGen-Plus approach (+2.61% for BP and +4.20% for MF). Further, fast convergence (converging in half the number of epochs) and efficient learning (in terms of very low difference between the training and validation losses) were also observed during the training process.

cs.LG↗

arXiv2019

EvoZip: Efficient Compression of Large Collections of Evolutionary Trees

Phylogenetic trees represent evolutionary relationships among sets of organisms. Popular phylogenetic reconstruction approaches typically yield hundreds to thousands of trees on a common leafset. Storing and sharing such large collection of trees requires considerable amount of space and bandwidth. Furthermore, the huge size of phylogenetic tree databases can make search and retrieval operations time-consuming. Phylogenetic compression techniques are specialized compression techniques that exploit redundant topological information to achieve better compression of phylogenetic trees. Here, we present EvoZip, a new approach for phylogenetic tree compression. On average, EvoZip achieves 71.6% better compression and takes 80.71% less compression time and 60.47% less decompression time than TreeZip, the current state-of-the-art algorithm for phylogenetic tree compression. While EvoZip is based on TreeZip, it betters TreeZip due to (a) an improved bipartition and support list encoding scheme, (b) use of Deflate compression algorithm, and (c) use of an efficient tree reconstruction algorithm. EvoZip is freely available online for use by the scientific community.

q-bio.PE↗

arXiv2019

A novel model for query expansion using pseudo-relevant web knowledge

In the field of information retrieval, query expansion (QE) has long been used as a technique to deal with the fundamental issue of word mismatch between a user's query and the target information. In the context of the relationship between the query and expanded terms, existing weighting techniques often fail to appropriately capture the term-term relationship and term to the whole query relationship, resulting in low retrieval effectiveness. Our proposed QE approach addresses this by proposing three weighting models based on (1) tf-itf, (2) k-nearest neighbor (kNN) based cosine similarity, and (3) correlation score. Further, to extract the initial set of expanded terms, we use pseudo-relevant web knowledge consisting of the top N web pages returned by the three popular search engines namely, Google, Bing, and DuckDuckGo, in response to the original query. Among the three weighting models, tf-itf scores each of the individual terms obtained from the web content, kNN-based cosine similarity scores the expansion terms to obtain the term-term relationship, and correlation score weighs the selected expansion terms with respect to the whole query. The proposed model, called web knowledge based query expansion (WKQE), achieves an improvement of 25.89% on the MAP score and 30.83% on the GMAP score over the unexpanded queries on the FIRE dataset. A comparative analysis of the WKQE techniques with other related approaches clearly shows significant improvement in the retrieval performance. We have also analyzed the effect of varying the number of pseudo-relevant documents and expansion terms on the retrieval effectiveness of the proposed model.

cs.IR↗

arXiv2019

Pitch-Synchronous Single Frequency Filtering Spectrogram for Speech Emotion Recognition

Convolutional neural networks (CNN) are widely used for speech emotion recognition (SER). In such cases, the short time fourier transform (STFT) spectrogram is the most popular choice for representing speech, which is fed as input to the CNN. However, the uncertainty principles of the short-time Fourier transform prevent it from capturing time and frequency resolutions simultaneously. On the other hand, the recently proposed single frequency filtering (SFF) spectrogram promises to be a better alternative because it captures both time and frequency resolutions simultaneously. In this work, we explore the SFF spectrogram as an alternative representation of speech for SER. We have modified the SFF spectrogram by taking the average of the amplitudes of all the samples between two successive glottal closure instants (GCI) locations. The duration between two successive GCI locations gives the pitch, motivating us to name the modified SFF spectrogram as pitch-synchronous SFF spectrogram. The GCI locations were detected using zero frequency filtering approach. The proposed pitch-synchronous SFF spectrogram produced accuracy values of 63.95% (unweighted) and 70.4% (weighted) on the IEMOCAP dataset. These correspond to an improvement of +7.35% (unweighted) and +4.3% (weighted) over state-of-the-art result on the STFT sepctrogram using CNN. Specially, the proposed method recognized 22.7% of the happy emotion samples correctly, whereas this number was 0% for state-of-the-art results. These results also promise a much wider use of the proposed pitch-synchronous SFF spectrogram for other speech-based applications.

eess.AS↗

arXiv2019

A new approach for query expansion using Wikipedia and WordNet

Query expansion (QE) is a well-known technique used to enhance the effectiveness of information retrieval. QE reformulates the initial query by adding similar terms that help in retrieving more relevant results. Several approaches have been proposed in literature producing quite favorable results, but they are not evenly favorable for all types of queries (individual and phrase queries). One of the main reasons for this is the use of the same kind of data sources and weighting scheme while expanding both the individual and the phrase query terms. As a result, the holistic relationship among the query terms is not well captured or scored. To address this issue, we have presented a new approach for QE using Wikipedia and WordNet as data sources. Specifically, Wikipedia gives rich expansion terms for phrase terms, while WordNet does the same for individual terms. We have also proposed novel weighting schemes for expansion terms: in-link score (for terms extracted from Wikipedia) and a tf-idf based scheme (for terms extracted from WordNet). In the proposed Wikipedia-WordNet-based QE technique (WWQE), we weigh the expansion terms twice: first, they are scored by the weighting scheme individually, and then, the weighting scheme scores the selected expansion terms concerning the entire query using correlation score. The proposed approach gains improvements of 24% on the MAP score and 48% on the GMAP score over unexpanded queries on the FIRE dataset. Experimental results achieve a significant improvement over individual expansion and other related state-of-the-art approaches. We also analyzed the effect on retrieval effectiveness of the proposed technique by varying the number of expansion terms.

cs.IR↗

arXiv2018

h-index and its alternative: A Review

In recent years, several Scientometrics and Bibliometrics indicators were proposed to evaluate the scientific impact of individuals, institutions, colleges, universities and research teams. The h-index gives a major breakthrough in the research community to evaluate the scientific impact of an individual. It got a lot of attention due to its simplicity and several other indicators were proposed to extend the properties of h-index as well as to overcome shortcomings of h-index. In this literature review, we have discussed the advantages and limitations of almost all Scientometrics as well as Bibliometrics indicators which have been categorized into seven categories :(i) Complement of h-index, (ii) Based on total number of authors, (iii) Based on publication age, (iv) Combination of two indices, (v) Based on excess citation count, (vi) Based on total publication count, (vii) Based on other variants. The main objective of this article is to study all those indicators which have been proposed to evaluate the scientific impact of an individual researcher or a group of researchers.

cs.DL↗

arXiv2018

Deep Robust Framework for Protein Function Prediction using Variable-Length Protein Sequences

Amino acid sequence portrays most intrinsic form of a protein and expresses primary structure of protein. The order of amino acids in a sequence enables a protein to acquire a particular stable conformation that is responsible for the functions of the protein. This relationship between a sequence and its function motivates the need to analyse the sequences for predicting protein functions. Early generation computational methods using BLAST, FASTA, etc. perform function transfer based on sequence similarity with existing databases and are computationally slow. Although machine learning based approaches are fast, they fail to perform well for long protein sequences (i.e., protein sequences with more than 300 amino acid residues). In this paper, we introduce a novel method for construction of two separate feature sets for protein sequences based on analysis of 1) single fixed-sized segments and 2) multi-sized segments, using bi-directional long short-term memory network. Further, model based on proposed feature set is combined with the state of the art Multi-lable Linear Discriminant Analysis (MLDA) features based model to improve the accuracy. Extensive evaluations using separate datasets for biological processes and molecular functions demonstrate promising results for both single-sized and multi-sized segments based feature sets. While former showed an improvement of +3.37% and +5.48%, the latter produces an improvement of +5.38% and +8.00% respectively for two datasets over the state of the art MLDA based classifier. After combining two models, there is a significant improvement of +7.41% and +9.21% respectively for two datasets compared to MLDA based classifier. Specifically, the proposed approach performed well for the long protein sequences and superior overall performance.

cs.LG↗

arXiv2018

EM and EM'-index sequence: Construction and application in scientific assessment of scholars

Most of the scientometric indicators use only the total number of citations of an article and produce a single number for scientific assessment of scholars. Although this concept is very simple to compute, it fails to show the scientific productivity and impact of scholars during a time-span or in a year. To overcome this, several time series indicators have been proposed that consider the citations from the entire research career of a scholar. However, these indicators fail to give a comparative assessment of two scholars having same or very similar index value. To overcome this shortcoming, h-index sequence was proposed to assess the impact of scholars during a particular time-span and to compare multiple scholars at a similar stage in their careers. The h-index sequence is based on the h-index formulation. One of the main issues related to the h-index is that it completely ignores the excess citation in scientific assessment; h-index sequence also exhibits a similar behaviour. To overcome these limitations, in this article, we have discussed the EM and $EM^{'}$-index sequence, and performed an empirical study based on yearly citation count earned from all publications of 89 scholars' publication data. The element of the EM and $EM^{'}$-index sequence for a given year shows the impact of a scholar for that year. We conclude that the EM and $EM^{'}$-index sequence could be used as an alternative metrics to asses the impact of scholars.

cs.DL↗

arXiv2018

DNN-HMM based Speaker Adaptive Emotion Recognition using Proposed Epoch and MFCC Features

Speech is produced when time varying vocal tract system is excited with time varying excitation source. Therefore, the information present in a speech such as message, emotion, language, speaker is due to the combined effect of both excitation source and vocal tract system. However, there is very less utilization of excitation source features to recognize emotion. In our earlier work, we have proposed a novel method to extract glottal closure instants (GCIs) known as epochs. In this paper, we have explored epoch features namely instantaneous pitch, phase and strength of epochs for discriminating emotions. We have combined the excitation source features and the well known Male-frequency cepstral coefficient (MFCC) features to develop an emotion recognition system with improved performance. DNN-HMM speaker adaptive models have been developed using MFCC, epoch and combined features. IEMOCAP emotional database has been used to evaluate the models. The average accuracy for emotion recognition system when using MFCC and epoch features separately is 59.25% and 54.52% respectively. The recognition performance improves to 64.2% when MFCC and epoch features are combined.

cs.SD↗

arXiv2017

Query expansion techniques for information retrieval: A survey

With the ever increasing size of the web, relevant information extraction on the Internet with a query formed by a few keywords has become a big challenge. Query Expansion (QE) plays a crucial role in improving searches on the Internet. Here, the user's initial query is reformulated by adding additional meaningful terms with similar significance. QE -- as part of information retrieval (IR) -- has long attracted researchers' attention. It has become very influential in the field of personalized social document, question answering, cross-language IR, information filtering and multimedia IR. Research in QE has gained further prominence because of IR dedicated conferences such as TREC (Text Information Retrieval Conference) and CLEF (Conference and Labs of the Evaluation Forum). This paper surveys QE techniques in IR from 1960 to 2017 with respect to core techniques, data sources used, weighting and ranking methodologies, user participation and applications -- bringing out similarities and differences.

cs.IR↗

arXiv2012

Extracting Conflict-free Information from Multi-labeled Trees

A multi-labeled tree, or MUL-tree, is a phylogenetic tree where two or more leaves share a label, e.g., a species name. A MUL-tree can imply multiple conflicting phylogenetic relationships for the same set of taxa, but can also contain conflict-free information that is of interest and yet is not obvious. We define the information content of a MUL-tree T as the set of all conflict-free quartet topologies implied by T, and define the maximal reduced form of T as the smallest tree that can be obtained from T by pruning leaves and contracting edges while retaining the same information content. We show that any two MUL-trees with the same information content exhibit the same reduced form. This introduces an equivalence relation in MUL-trees with potential applications to comparing MUL-trees. We present an efficient algorithm to reduce a MUL-tree to its maximally reduced form and evaluate its performance on empirical datasets in terms of both quality of the reduced tree and the degree of data reduction achieved.

cs.DS↗