Search

Diagnostic theories are fundamental to information system (IS) practice and are represented as trees. While there are approaches for validating diagnostic trees, these validate the overall performance of the tree rather than identifying ways incorrect diagnoses can occur. It is important to fully validate diagnostic trees because even if the tree gives the correct decision “most of the time,” it is possible for incorrect decisions traveling down little-used branches of the tree to result in catastrophic decisions. In this article, we describe the process of using a variant of q-sorting to validate diagnostic trees. In this methodology, diagnostic trees that independent experts develop are transformed into a quantitative form, and that quantitative form is tested to determine the inter-rater reliability of the individual branches in the tree. The trees are then successively transformed to incrementally test if they branch in the same way. The results help researchers not only identify quality items for use in a diagnostic tree but also facilitate diagnoses of problems with those items and facilitate the reconciliation of discrepant trees by experts. The methodology validates not only the whole tree but also its subparts.

Tree fruit architecture results from combination of the training system and pruning and thinning processes across multiple growth and development years. Further, the tree fruit architecture contributes to the light interception and improves tree growth, fruit quality, and fruit yield, in addition to easing the process of orchard management and harvest. Currently tree architectural traits are measured manually by researchers or growers, which is labor-intensive and time-consuming. In this study, the remote sensing techniques were evaluated to phenotype critical architectural traits with the final goal to assist tree fruit breeders, physiologists and growers in collecting architectural traits efficiently and in a standardized manner. For this, a consumer-grade red–green–blue (RGB) camera was used to collect apple tree side-images, while an unmanned aerial vehicle (UAV) integrated RGB camera was programmed to image tree canopy at 15 m above ground level to evaluate multiple tree fruit architectures. The sensing data were compared to ground reference data associated with tree orchard blocks within three training systems (Spindle, V-trellis, Bi-axis), two rootstocks (‘WA 38 trees grafted on G41 and M9-Nic29) and two pruning methods (referred as bending and click pruning). The data were processed to extract architectural features from ground-based 2D images and UAV-based 3D digital surface model. The traits extracted from sensing data included box-counting fractal dimension (DBs), middle branch angle, number of branches, trunk basal diameter, and tree row volume (TRV). The results from ground-based sensing data indicated that there was a significant (P

With the popularization of location-based services (LBS), encryption techniques have been utilized to protect data security when outsourcing LBS to cloud. However, existing schemes only consider spatial range search or keyword search, while expressive and practical search over encrypted LBS data is still a challenging problem. In this paper, we introduce PrivSTL, a privacy-preserving spatio-temporal keyword search framework over the encrypted LBS data based on attribute-based encryption and linear encryption. It allows mobile users to submit LBS query with spatial range, time interval and Boolean keyword expression, and provides accurate and authorized search by matching these query conditions and also the access policy. Then we introduce an extended scheme PrivSTG, which utilizes Geohash to divide the locations into grids, and outsources an encrypted index tree to cloud servers. PrivSTG improves the service efficiency by searching only over the ciphertexts in the surrounding grids of mobile user. Finally, we analyze the security of PrivSTL against chosen-plaintext, chosen-keyword and outside keyword-guessing attacks in generic bilinear group model, and show that PrivSTL guarantees the spatio-temporal keyword profile privacy, and also protects the query privacy of mobile user. The experimental results indicate that our scheme is practical and efficient for outsourced LBS.

The proposed work aims to solve data sparsity problem in the recommendation system. It handles two-level pre-processing techniques to reduce the data size at the item level. Additional resources like items genre, tag, and time are added to learn and analyse the behaviour of the user preferences in-depth. The advantage of the proposed method is to recommend the item, based on user interest pattern and avoid recommending the outdated items. User information are grouped based on similar item genre and tag feature. This effectively handle overlapping conditions that exist on item’s genre, as it has more than one genre at initial level. Further, based on time, it analyses the user non-static interest. Overall it reduces the dimensions which is an initial way to prepare data, to analyse hidden pattern. To enhance the performance, the proposed method utilized Apache’s spark Mllib FP-Growth and association rule mining approach in a distributed environment. To reduce the computation cost of constructing tree in FP-Growth, the candidate data set is stored in matrix form. The experiments were conducted using MovieLens data set. The observed results shows that the proposed method achieves 4% increase in accuracy when compared to earlier methods.

Currently, there are many simultaneous localization and mapping (SLAM) algorithms for 3-D light detection and ranging (lidar) relying on features such as planes and edges. However, if a robot needs to work in a rubber forest, these simple features can be unstable due to the complexity of the environment. To address this problem, in this article, we propose the first SLAM system to make a deep adaptive adjustment for the particularity of the rubber-tapping robot and the rubber forest environment. In our article, tree trunks are used to construct a set of sparse maps called trunk atlas, which contain environmental information for localization and trunk position for rubber tapping. To ensure the quality of feature extraction, density field correction and multicriteria trunk detection are proposed. Due to the sparsity and stability of the trunk atlas, our SLAM system can ensure real-time performance. Experiments show that our lidar-only SLAM system can achieve nearly the same performance as state-of-the-art inertial-measurement-unit-aided algorithms in terms of runtime and localization accuracy. In addition, our trunk atlas also takes up less memory for storage than other algorithms. More specifically, it takes less than 50 kB to store a map of an area of approximately 5000 m $^2$ .

In the field of information visualization, the concept of "tasks" is an essential component of theories and methodologies for how a visualization researcher or a practitioner understands what tasks a user needs to perform and how to approach the creation of a new design. In this article, we focus on the collection of tasks for tree visualizations, a common visual encoding in many domains ranging from biology to computer science to geography. In spite of their commonality, no prior efforts exist to collect and abstractly define tree visualization tasks. We present a literature review of tree visualization articles and generate a curated dataset of over 200 tasks. To enable effective task abstraction for trees, we also contribute a novel extension of the Multi-Level Task Typology to include more specificity to support tree-specific tasks as well as a systematic procedure to conduct task abstractions for tree visualizations. All tasks in the dataset were abstracted with the novel typology extension and analyzed to gain a better understanding of the state of tree visualizations. These abstracted tasks can benefit visualization researchers and practitioners as they design evaluation studies or compare their analytical tasks with ones previously studied in the literature to make informed decisions about their design. We also reflect on our novel methodology and advocate more broadly for the creation of task-based knowledge repositories for different types of visualizations. The Supplemental Material, which can be found on the Computer Society Digital Library at http://doi.ieeecomputersociety.org/10.1109/TVCG.2021.3064037, will be maintained on OSF: https://osf.io/u5ehs/.

Traditional searchable encryption schemes based on the Term Frequency-Inverse Document Frequency (TF-IDF) model adopt the presence of keywords to measure the relevance of documents to queries, which ignores the latent semantic meanings that are concealed in the context. Latent Dirichlet Allocation (LDA) topic model can be utilized for modeling the semantics among texts to achieve semantic-aware multi-keyword search. However, the LDA topic model treats queries and documents from the perspective of topics, and the keywords information is ignored. In this paper, we propose a privacy-preserving searchable encryption scheme based on the LDA topic model and the query likelihood model. We extract the feature keywords from the document using the LDA-based Information Gain (IG) and Topic Frequency-Inverse Topic Frequency (TF-ITF) model. With feature keyword extraction and the query likelihood model, our scheme can achieve a more accurate semantic-aware keyword search. A special index tree is used to enhance search efficiency. The secure inner product operation is utilized to implement the privacy-preserving ranked search. The experiments on real-world datasets demonstrate the effectiveness of our scheme.

Music Information Retrieval (MIR) is the task of extracting high-level information, such as genre, artist or instrumentation from music. Genre classification is an important and rapidly evolving research area of MIR. To date, only a small amount of research work has been done on the automatic genre classification of Nigerian songs. Hence, this study presents a new music dataset, namely the ORIN dataset, consisting of only Nigerian songs. The study dataset contains 478 Nigerian traditional songs from five genres: fuji, juju, highlife, waka and apala. The timbral texture and tempo features were mined from 30-second segments of each song using the Librosa Python library. For genre classification, the ORIN datasets was trained on 4 different classifiers- k-Nearest Neighbhour, Support Vector Machine, eXtreme Gradient Boosting (XGBoost) and Random Forest- with 85–15 train-test splits. The results obtained for the five different genres indicates that XGBoost classifier is a better model, having the highest accuracy of 81.94% and recall of 84.57%. This study uses the global mean (Tree SHAP) method to determine feature importance and impact on the classification model. Further analysis on the individual genres found some nearness in the timbral properties between some of the genres. This analysis was confirmed by human observation.

The advance of smart eHealthcare has greatly enabled patients to enjoy high-quality healthcare services, e.g., disease prediction. Meanwhile, to support the dramatic increase of healthcare data, healthcare centers often outsource the on-premises data to the cloud. However, since the healthcare data contain some sensitive information and the cloud server is not fully trusted, healthcare centers need to encrypt the data before outsourcing them. Unfortunately, data encryption inevitably hinders some advanced data applications like the similarity range query. Although many studies on similarity range queries over encrypted data have been reported, most of them still have some limitations in security, efficiency, accuracy, and practicality. Aiming at this challenge, in this paper, we propose an efficient, privacy-preserving, and practical similarity range query (EPSim) scheme. Specifically, we first present a modified asymmetric scalar-product-preserving encryption (ASPE) scheme and prove its security. Then, we introduce a Quadsector tree to represent the data and employ a filtration condition to design an algorithm for efficient similarity range queries over the Quadsector tree. Finally, we propose our EPSim scheme by integrating the modified ASPE scheme and Quadsector tree. Detailed security analysis and performance evaluations indicate our scheme is really secure and efficient in similarity range queries.

Underwater wireless acoustic networks (UWANs) take advantage of acoustic communication to enable many distinct applications. The peculiar features of underwater acoustic channels, such as long propagation delay, high bit error rates, and severely limited bandwidth, make the use of medium access control (MAC) solutions designed for terrestrial radio networks inefficient in UWANs. This paper proposes UW-SEEDEX, a MAC protocol for UWANs that employs random time slot schedules, created from seeds, to avoid collisions. After exchanging seeds, nodes can know other's entire schedules, allowing them to then better plan their transmissions. Simulations evaluate how each of UW-SEEDEX's parameter affects its performance in metrics such as end-to-end delay, energy consumption, transmissions per data reception, and reception rate using different test scenarios. Simulations also show that UW-SEEDEX can perform better than other MAC solutions, delivering more messages than protocols such as UW-Aloha and Slotted FAMA and reduced, on average, up to three times the number of transmissions required for each message reception in networks with grid topologies. UW-SEEDEX presented reception rates close to 100%, low energy cost, and fewer transmissions per data reception. Our code is available at https://gitlab.com/epmcj/ns-3-dev/-/tree/new-uan-mac-protocols.

Context based API recommendation is an important way to help developers find the needed APIs effectively and efficiently. For effective API recommendation, we need not only a joint view of both structural and textual code information, but also a holistic view of correlated API usage in control and data flow graph as a whole. Unfortunately, existing API recommendation methods exploit structural or textual code information separately. In this work, we propose a novel API recommendation approach called APIRec-CST (API Recommendation by Combining Structural and Textual code information). APIRec-CST is a deep learning model that combines the API usage with the text information in the source code based on an API Context Graph Network and a Code Token Network that simultaneously learn structural and textual features for API recommendation. We apply APIRec-CST to train a model for JDK library based on 1,914 open-source Java projects and evaluate the accuracy and MRR (Mean Reciprocal Rank) of API recommendation with another 6 open-source projects. The results show that our approach achieves respectively a top-1, top-5, top-10 accuracy and MRR of 60.3%, 81.5%, 87.7% and 69.4%, and significantly outperforms an existing graph-based statistical approach and a tree-based deep learning approach for API recommendation. A further analysis shows that textual code information makes sense and improves the accuracy and MRR. The sensitivity analysis shows that the top-k accuracy and MRR of APIRec-CST are insensitive to the number of APIs to be recommended in a hole. We also conduct a user study in which two groups of students are asked to finish 6 programming tasks with or without our APIRec-CST plugin. The results show that APIRec-CST can help the students to finish the tasks faster and more accurately and the feedback on the usability is overwhelmingly positive.

The glaucoma is an eye disease that causes blindness when it progresses in an advanced stage. Early glaucoma diagnosis is essential to prevent the vision loss. However, early detection is not covered due to the lack of ophthalmologists and the limited accessibility to retinal image capture devices. In this paper, we present an automated method for glaucoma screening dedicated for Smartphone Captured Fundus Images (SCFIs). The implementation of the method into a smartphone associated to an optical lens for retina capturing leads to a mobile aided screening system for glaucoma. The challenge consists in insuring higher performance detection despite the moderate quality of SCFIs, with a reduced execution time to be adequate for the clinical use. The main idea consists in deducing glaucoma based on the vessel displacement inside the Optic Disk (OD), where the vessel tree remains sufficiently modeled on SCFIs. Within this objective, our major contribution consists in proposing: (1) a robust processing for locating vessel centroids in order to adequately model the vessel distribution, and (2) a feature vector that relevantly reflect two main glaucoma biomarkers in terms of vessel displacement. Furthermore, all processing steps are carefully chosen based on lower complexity, to be suitable for fast clinical screening. A first evaluation of our method is performed using the two public DRISHTI-DB and DRIONS-DB databases, where 99% and 95% accuracy, 96.77% and 97,5% specificity and 100% and 95% sensitivity are respectively achieved. Thereafter, the method is evaluated using two fundus image databases respectively captured through a smartphone and retinograph for the same persons. We achieve 100% accuracy using both databases which assesses the robustness of our method. In addition, the detection is performed on 0.027 and 0.029 second when executed respectively on the Samsung-M51 on the Samsung-A70 smartphone devices. Our proposed smartphone app provides a cost-effective and widely accessible mobile platform for early screening of glaucoma in remote clinics or areas with limited access to fundus cameras and ophthalmologists.

Cloud storage attracts a lot of clients to join the paradise. For a high data availability, some clients require their files to be replicated and stored on multiple servers. Because clients are generally charged based on the redundancy level required by them, it is critical for clients to obtain convincing evidence that all replicas are stored correctly and are updated to the up-to-date version. In this paper, we propose a dynamic proof of data possession and replication (DPDPR) scheme, which is proved to be secure in the defined security model. Our scheme shares a single authenticated tree across multiple replicas, which reduces the tree's storage cost significantly. Our scheme allows for batch verification for multiple challenged leaves and can verify multiple replicas in a single batch way, which considerably save bandwidth and computation resources during audit process. We also evaluate the DPDPR's performance and compare it with the most related scheme. The evaluation results show that our scheme saves almost 66% tree's storage cost for three replicas, and obtains almost 60% and 80% efficiency improvements in terms of the overall bandwidth and computation costs, respectively, when three replicas are checked and each challenged with 460 blocks.

Most of the classification methods of urban functional areas nowadays are only based on single source data analysis and modeling, which can not make full use of the multi-scale and multi-source data that is easy to obtain. Therefore, this paper proposed a classification model of urban functional areas based on multi-modal machine learning, by analyzing regional remote sensing images and behavior data of visitors in the area, using the combination of supervised methods extracted the deep-seated features and relationships of kinds of data, filtered and merged the overall and local features of the data. The model used dual branch neural network combining SE-ResNeXt and Dual Path Network (DPN) to automatically mined and fused the overall characteristics of multi-source data, and used the designed feature engineering to deeply mine the behavior data of users to obtain more association information, then combined the algorithm based on Gradient Boosting Decision Tree to learn the characteristics of different levels and obtained the classification probability for different levels of features. Finally, we continued to use the algorithm based on the Gradient Boosting Decision Tree to learn the probability distribution of different levels of features to obtain the final prediction results of urban functional area classification. Through the analysis and experimental verification of real data sets, the results showed that MM-UrbanFAC model can effectively integrate the features of multi-modal data. Compared with a single classifier, the integration framework based on gradient lifting tree improved the prediction performance, this method can effectively integrate the results of multiple models and accurately classify urban functional areas, and the model can provide reference for tourism recommendation, urban land planning and urban construction.

Internet of Things (IoT) devices and systems are becoming increasingly commonplace, and as such systems scale up, so do the computational and storage requirements. Hence, one recent trend is to outsource data from IoT devices to remote systems. To facilitate both ciphertext retrieval and data confidentiality in the outsourced data, a number of searchable encryption approaches have been proposed in the literature. However, due to limited keyword space, a number of searchable encryption schemes are vulnerable to keyword guessing attacks (KGA). In addition, existing searchable encryption approaches generally do not consider the hierarchical structure in which users at different levels require varying access privileges. Furthermore, existing searchable encryption schemes seldom provide time-controlled access control. Therefore, in this paper we propose a time-controlled hierarchical multi-keyword search by using a double-server architecture to mitigate KGA. In our approach, we also build a public key tree to support different access permissions for hierarchical users. Formal security analysis shows that our scheme is secure, and extensive experiments demonstrate that our scheme is practical.

This article proposes a binary tree of classifiers for multi-label classification that preserves label dependencies and handles class imbalance. At each node, the input data is strategically split into two subsets for its subsequent child nodes, keeping the label correlations intact. A novel approach of partitioning the data based on label-set proximity has also been proposed. Various data appropriate classifiers are trained to learn the binary partition at every internal node. The tree of classifiers grows iteratively depending on two parameters – multi-label entropy and sample cardinality, computed on the data at the current node. During training, the decision at any node is based on these parameters and the branching out is restricted, if deemed unnecessary. Specific classifiers at the leaf nodes perform the final classification task and assign appropriate label-sets to the unlabelled data. The proposed system aims to appropriately split the data and build the hierarchical structure such that the training and classification tasks become simpler. Also, the problem of class imbalance leads to the irregular splitting of data and excessive branching out of the tree which is handled through the novel use of suitable classifiers and parameters at the intermediate and leaf nodes. The proposed method has shown significant performance improvement on fourteen datasets against fourteen existing multi-label classifiers. Two-tailed Wilcoxon signed rank test statistics show that for $T_{Wilcoxon}(14,0.2)=31$ the proposed method outperforms all the other comparison models.

Decision tree is a widely used non-parametric technique in machine learning, data mining and pattern recognition. It is simple to understand and interpret, however it faces challenges such as handling higher dimensional and class imbalanced datasets, over-fitting and instability. To overcome some of these issues, vertical partitioning approaches like serial partitioning, theme based partitioning are used in the literature. A vertical partitioning approach divides the feature set into subsets of features (blocks) and makes use of these subsets for subsequent tasks. In this work, we use the ideas of music rhythm tree to propose a novel vertical partitioning technique. It orders the features based on the average correlation strength of the features before partitioning the feature set. The proposed method is proved to be superior by showing an average of 13.8 % , 6 % , 9.8 % , 19.7 % , 9.4 % , and 29.4 % higher classification accuracy over C4.5, Random Forest, Bagging, Adaboost, an ensemble technique and a vertical partitioning technique respectively. Our empirical results on 15 datasets demonstrate that the proposed vertical partitioning method is more stable and better in handling class-imbalanced data. Finally, some popular statistical tests are conducted to validate the statistical significance of the results of the proposed method.

Well known oil recovery factor estimation techniques such as analogy, volumetric calculations, material balance, decline curve analysis, hydrodynamic simulations have certain limitations. Those techniques are time-consuming, require specific data and expert knowledge. Besides, though uncertainty estimation is highly desirable for this problem, the methods above do not include this by default. In this work, we present a data-driven technique for oil recovery factor (limited to water flooding) estimation using reservoir parameters and representative statistics. We apply advanced machine learning methods to historical worldwide oilfields datasets (more than 2000 oil reservoirs). The data-driven model might be used as a general tool for rapid and completely objective estimation of the oil recovery factor. In addition, it includes the ability to work with partial input data and to estimate the prediction interval of the oil recovery factor. We perform the evaluation in terms of accuracy and prediction intervals coverage for several tree-based machine learning techniques in application to the following two cases: (1) using parameters only related to geometry, geology, transport, storage and fluid properties, (2) using an extended set of parameters including development and production data. For both cases model proved itself to be robust and reliable. We conclude that the proposed data-driven approach overcomes several limitations of the traditional methods and is suitable for rapid, reliable and objective estimation of oil recovery factor for hydrocarbon reservoir.

In vehicle operation, in order to maximize the fuel economy, the propulsion system control can easily adapt to pressure and temperature variations as these variations can be measured by sensors. However, it is challenging to detect driving cycles. With growing progress made in the artificial intelligence field, pattern recognition gains momentum in various applications. This study presents a study on driving cycle pattern recognition based on supervised learning. Training data 2-D visualization is achieved by t-SNE algorithm. Ten out of twelve supervised learning algorithms predict driving conditions with the accuracy at 88% or higher and Extra Tree algorithm leads the recognition accuracy at 90.26%. To improve recognition accuracy, two hierarchical frameworks are proposed by integrating multiple supervised learning methods using weighted average and vote methods. The two hierarchical frameworks boost the driving condition recognition accuracy from 90.26% to 90.43% (weighted average) and 91.76% (vote). The results are further validated in holdout test. Additionally, a plug-in hybrid electric vehicle simulation shows 3.88%-5.82% fuel economy improvement when compared to baseline method. Two hierarchical methods outperform the Extra Tree method by 2% fuel economy. In summary, supervised learning shows great potential to detect driving cycles for vehicle energy saving.

Searchable encryption enables users to perform a keyword-based search over encrypted data. Most of the existing searchable encryption schemes are based on the single cloud server model, which has some limitations, such as the single point of failure and malicious insiders. In contrast, the multicloud server model has higher data availability and security. However, directly moving the existing keyword search schemes to the multicloud would cause larger storage and search costs, and the data security cannot be distinctly improved. In addition, different from single cloud, a challenge is how to effectively verify query integrity when some cloud servers return incorrect or incomplete results in a multicloud situation. To ensure the data security, we propose an iterative encryption method to ensure the file privacy even if multiple cloud servers collude with each other. We use Bloom filter to map keywords and construct a tree index for each cloud server to achieve secure and efficient distributed keyword search. To verify the query integrity, we propose a fast verification algorithm to embed the file content and index information into the file ID. The analysis and experiments demonstrate the security and effectiveness of our scheme.

Publisher Copyright: IEEE Copyright: Copyright 2021 Elsevier B.V., All rights reserved. We consider learning to play multiplayer imperfect-information games with simultaneous moves and large state-action spaces. Previous attempts to tackle such challenging games have largely focused on model-free learning methods, often requiring hundreds of years of experience to produce competitive agents. Our approach is based on model-based planning. We tackle the problem of partial observability by first building an (oracle) planner that has access to the full state of the environment and then distilling the knowledge of the oracle to a (follower) agent which is trained to play the imperfect-information game by imitating the oracle's choices. We experimentally show that planning with naive Monte Carlo tree search performs poorly in large combinatorial action spaces. We therefore propose planning with a fixed-depth tree search and decoupled Thompson sampling for action selection. We show that the planner is able to discover efficient playing strategies in the games of Clash Royale and Pommerman and the follower policy successfully learns to implement them by training on few hundred battles.

Due to its strong performance in handling uncertain and ambiguous data, the fuzzy k -nearest-neighbor method (FKNN) has realized substantial success in a wide variety of applications. However, its classification performance would be heavily deteriorated if the number k of nearest neighbors was unsuitably fixed for each testing sample. This study examines the feasibility of using only one fixed k value for FKNN on each testing sample. A novel FKNN-based classification method, namely, fuzzy KNN method with adaptive nearest neighbors (A-FKNN), is devised for learning a distinct optimal k value for each testing sample. In the training stage, after applying a sparse representation method on all training samples for reconstruction, A-FKNN learns the optimal k value for each training sample and builds a decision tree (namely, A-FKNN tree) from all training samples with new labels (the learned optimal k values instead of the original labels), in which each leaf node stores the corresponding optimal k value. In the testing stage, A-FKNN identifies the optimal k value for each testing sample by searching the A-FKNN tree and runs FKNN with the optimal k value for each testing sample. Moreover, a fast version of A-FKNN, namely, FA-FKNN, is designed by building the FA-FKNN decision tree, which stores the optimal k value with only a subset of training samples in each leaf node. Experimental results on 32 UCI datasets demonstrate that both A-FKNN and FA-FKNN outperform the compared methods in terms of classification accuracy, and FA-FKNN has a shorter running time.

Recent efforts applying machine learning techniques to query optimization have shown few practical gains due to substantive training overhead, inability to adapt to changes, and poor tail performance. Motivated by these difficulties, we introduce Bao (the \underlineBa ndit \underlineo ptimizer). Bao takes advantage of the wisdom built into existing query optimizers by providing per-query optimization hints. Bao combines modern tree convolutional neural networks with Thompson sampling, a well-studied reinforcement learning algorithm. As a result, Bao automatically learns from its mistakes and adapts to changes in query workloads, data, and schema. Experimentally, we demonstrate that Bao can quickly learn strategies that improve end-to-end query execution performance, including tail latency, for several workloads containing long-running queries. In cloud environments, we show that Bao can offer both reduced costs and better performance compared with a commercial system.

The explosive growth of modern web-scale applications has made cost-effectiveness a primary design goal for their underlying databases. As a backbone of modern databases, LSM-tree based key–value stores (LSM store) face limited storage options. They are either designed for local storage that is relatively small, expensive, and fast or for cloud storage that offers larger capacities at reduced costs but slower. Designing an LSM store by integrating local storage with cloud storage services is a promising way to balance the cost and performance. However, such design faces challenges such as data reorganization, metadata overhead, and reliability issues. In this article, we propose RocksMash , a fast and efficient LSM store that uses local storage to store frequently accessed data and metadata while using cloud to hold the rest of the data to achieve cost-effectiveness. To improve metadata space-efficiency and read performance, RocksMash uses an LSM-aware persistent cache that stores metadata in a space-efficient way and stores popular data blocks by using compaction-aware layouts. Moreover, RocksMash uses an extended write-ahead log for fast parallel data recovery. We implemented RocksMash by embedding these designs into RocksDB. The evaluation results show that RocksMash improves the performance by up to 1.7 \( \times \) compared to the state-of-the-art schemes and delivers high reliability, cost-effectiveness, and fast recovery.

Cloud storage becomes the priority for storing and sharing data for enterprise users. Encrypting prior to uploading data to the cloud is the best way to protect business secrets, however, it hinders the convenient operations on plaintexts, such as searching over the cloud data. In addition, employees in an enterprise have multiple layer structures and a higher layer employee should have the privilege to monitor the lower layer employees' data to check if these users violate the regulation without letting the employees be aware of. Public key encryption with keyword search (PEKS) is a well-known cryptographic primitive suitable for secure cloud storage, which supports keyword search without decryption in public key encryption settings. Unfortunately, there is no existing PEKS scheme supporting the monitoring function without authorization from the sender. To address this issue, we propose a variant of PEKS named Hierarchical Public Key Encryption with Keyword Search (HPEKS) and provide a semi-generic construction utilizing a public key tree (PKTree) and a PEKS scheme. To better suit for the enterprise secret data sharing, we build an advanced HPEKS scheme, named designated-tester decryptable hierarchical public key encryption with keyword search, which enjoys stronger security and integrates the public key and symmetric key.

A key element in solving real-life data science problems is selecting the types of models to use. Tree ensemble models (such as XGBoost) are usually recommended for classification and regression problems with tabular data. However, several deep learning models for tabular data have recently been proposed, claiming to outperform XGBoost for some use cases. This paper explores whether these deep models should be a recommended option for tabular data by rigorously comparing the new deep models to XGBoost on various datasets. In addition to systematically comparing their performance, we consider the tuning and computation they require. Our study shows that XGBoost outperforms these deep models across the datasets, including the datasets used in the papers that proposed the deep models. We also demonstrate that XGBoost requires much less tuning. On the positive side, we show that an ensemble of deep models and XGBoost performs better on these datasets than XGBoost alone.

With the development of cloud computing, more and more data owners are motivated to outsource their documents to the cloud and share them with the authorized data users securely and flexibly. To protect data privacy, the documents are generally encrypted before being outsourced to the cloud and hence their searchability decreases. Though many privacy-preserving document search schemes have been proposed, they cannot reach a proper balance among functionality, flexibility, security and efficiency. In this paper, a new encrypted document retrieval system is designed and a proxy server is integrated into the system to alleviate data owner's workload and improve the whole system's security level. In this process, we consider a more practical and stronger threat model in which the cloud server can collude with a small number of data users. To support multiple document search patterns, we construct two AVL trees for the filenames and authors, and a Hierarchical Retrieval Features tree (HRF tree) for the document vectors. A depth-first search algorithm is designed for the HRF tree and the Enhanced Asymmetric Scalar-Product-Preserving Encryption (Enhanced ASPE) algorithm is utilized to encrypt the HRF tree. All the three index trees are linked with each other to efficiently support the search requests with multiple parameters. Theoretical analysis and simulation results illustrate the security and efficiency of the proposed framework.

Localization in the complex urban environment is an open problem for current methods. The occlusion from dynamic objects, such as vehicles and pedestrians, degenerates the precision of the localization result. This article proposes a pole-like feature-based localization framework to solve this problem. Pole-like objects, such as posts of lamps or traffic sign and tree trunks, widely exist in the urban environment and are robust to occlusion, as they are usually higher than the objects on the road. First, this type of feature is extracted from the point cloud by a robust clustering algorithm. Then, the features from different frames of data are stitched to generate a feature map. For online localization, a Monte Carlo localization (MCL) framework is used to fuse the vehicle motion data and the map-matching result. An improved version of iterative closest point (ICP) that is specifically designed for the pole-like feature association is used for map matching based on the state of every particle. With the MCL scheme, localization is robust to the local minimum or robot kidnapping problem. Experimental results in the real urban environment demonstrate the precision and robustness of the proposed method, with mean absolute errors less than 0.20 m and 0.5°. The results also show that the proposed method outperforms some state-of-the-art localization methods in the complex urban environment.

Energy is one of the most important requirements for countries and serves as an indicator of the development level of a country. Developments in social, economic and industrial areas have increased the energy needs of countries. Solar energy is one of the most promising renewable energy sources to meet increased energy demands. Photovoltaic (PV) models used to generate electricity from solar energy are among the most popular renewable energy systems. To obtain maximum efficiency from PV models, it is very important to estimate parameters based on current–voltage data, simulate and control PV models for electricity generation. To achieve maximum efficiency for PV models, their parameters should be estimated in an optimum way. Therefore, tree seed algorithm (TSA) developed inspired by nature was proposed in this study. TSA is a meta-heuristic algorithm inspired by the connection between trees and seeds and proposed for solving continuous optimization problems. Parameters of three different PV models (single diode model, double diode model and PV module) were optimized with TSA. Various analyses were performed to prove the success of the proposed method in parameter optimization of PV models. The results were also compared with those of similar studies in the literature. The analysis results indicated that the proposed method yielded very successful, effective and reliable results, and it was concluded that it was a competitive method compared to other methods in the literature.

In this article, a virtual-goal-guided rapidly exploring random tree (RRT)-based visual servoing approach is proposed for nonholonomic mobile robots to simultaneously satisfy the field-of-view (FOV) constraint and the velocity constraints during the motion toward the desired pose. The presented approach contains two parts: 1) trajectory planning in the scaled Euclidean space and 2) trajectory tracking control. For the trajectory planning part, a new virtual-goal-guided RRT algorithm is designed to guarantee the FOV constraint and the velocity constraints by iteratively exploring the scaled Euclidean space in the presence of unknown image depth. Specifically, a virtual goal directly behind the desired pose is set to guide the tree to extend laterally into the area wherein the robot is easier to satisfy the FOV constraint. In addition, the lateral extension of the tree also helps decrease the lateral error of the robot as much as possible. Following each successful extension toward the virtual goal node, a greedy extension from the newly explored node to the desired pose is attempted using a polar stabilization controller, so that the planned trajectory can accurately arrive at the desired pose. Each newly explored edge in the scaled space is projected into the image space to check for the FOV limit. For the visual tracking part, the final searched trajectory in the scaled space is first transformed into image feature trajectories, which are then tracked by an image-based visual tracking controller. Experiments validate the effectiveness of the proposed approach.

Background Young people are vulnerable to experiencing problematic levels of loneliness which can lead to poor mental health outcomes. Loneliness is a malleable treatment target and preliminary evidence has shown that it can be addressed with digital platforms. Peer Tree is a strength-based digital smartphone application aimed at reducing loneliness. The study aim is to reduce loneliness and assess the acceptability, usability, and feasibility of Peer Tree in young people enrolled at university. Methods This will be a pilot randomised controlled trial (RCT) comparing a strength-based digital smartphone application (Peer Tree) with a control condition. Forty-two young people enrolled at university will be recruited for this pilot RCT. Participants with suicidal ideation or behaviours, acute psychiatric symptoms in the past month, or a current diagnosis of a mood or social anxiety disorder will be excluded. Allocation will be made on a 1:1 ratio and will occur after the initial baseline assessment. Assessments are completed at baseline, at post-intervention, and at follow-up. Participants in the control condition complete the same three assessment sessions. The primary outcome of the study will be loneliness. Depression, social anxiety, quality of life, acceptability, usability, feasibility, and safety of Peer Tree will also be measured as secondary outcomes. Discussion This trial will report the findings of implementing Peer Tree, a smartphone application aimed at reducing loneliness in university students. Findings from this trial will highlight the initial efficacy, acceptability, and feasibility of using digital positive psychology interventions to reduce subthreshold mental health concerns. Findings from this trial will also describe the safety of Peer Tree as a digital tool. Results will contribute evidence for positive psychology interventions to address mental ill-health. Trial registration Australian New Zealand Clinical Trial Registry ACTRN12619000350123. Registered on 6 March 2020

Predicting transportation mode choice is a critical component of forecasting travel demand. Recently, machine learning methods have become increasingly more popular in predicting transportation mode choice. Class association rules (CARs) have been applied to transportation mode choice, but the application of the imputed rules for prediction remains a long-standing challenge. Based on CARs, this paper proposes a new rule merging approach, called CARM, to improve predictive accuracy. In the suggested approach, first, CARs are imputed from the frequent pattern tree (FP-tree) based on the frequent pattern growth (FP-growth) algorithm. Next, the rules are pruned based on the concept of pessimistic error rate. Finally, the rules are merged to form new rules without increasing predictive error. Using the 2015 Dutch National Travel Survey, the performance of suggested model is compared with the performance of CARIG that uses the information gain statistic to generate new rules, class-based association rules (CBA), decision trees (DT) and the multinomial logit (MNL) model. In addition, the proposed model is assessed using a ten-fold cross validation test. The results show that the accuracy of the proposed model is 91.1%, which outperforms CARIG, CBA, DT and the MNL model.

This paper briefly describes Amanda(1), a framework for mediating collective discussions in distance learning environments. The objective of this framework is to help tutors achieve better results from group discussions and improve knowledge transfer among the participants. The overall idea is to organize the group discussion in an argumentation tree and involve the participants in successive discussion activities. The coordination of the discussion is made by a set of intelligent mechanisms which reason over the discussion and propose new interactions among the participants. Amanda advances the discussion by generating progressive discussion cycles until a desired set of target conditions are observed. At each discussion cycle, the system redistributes discussion tasks among the participants to ensure a desired degree of agreement and participation among them. In this short paper we describe the underlying coordination principles and the use of knowledge models for producing natural language questions.

The availability of big data spurred the application of modern prediction analytics (e.g., machine learning methods) in human resource management (HRM) research and practice. Due to the novel and technical nature of prediction analytics, HR professionals and researchers may struggle to collaborate with data experts. We offer a comprehensive introduction to the logic and value of prediction methods. Moreover, we highlight the concern of treating grouped data—commonly seen in HRM research yet rarely discussed in building prediction models. We introduce different strategies to deal with grouped data in applying prediction models. The performance of different modelling approaches and prediction models are compared in an empirical data set consisting of 1454 employees from 199 small and medium sized enterprise's. Following a workflow to compare the relative performance of the prediction models, the model with the best prediction accuracy was the random-effects bagged tree that allows for complex relationships and incorporates random effects. Following the estimates of this model, we identified the five most influential predictors of turnover intention: perceived fairness, leader-member exchange, career opportunities, pay satisfaction and age. The inductive nature of prediction models is expected to advance theory development and HR analytics for developing effective HRM policies.

Identity recognition plays an important role in ensuring security in our daily life. Biometric-based (especially activity-based) approaches are favored due to their fidelity, universality, and resilience. However, most existing machine learning-based approaches rely on a traditional workflow where models are usually trained once for all, with limited involvement from end-users in the process and neglecting the dynamic nature of the learning process. This makes the models static and can not be updated in time, which usually leads to high false positive or false negative. Thus, in practice, an expert is desired to assist with providing high-quality observations and interpretation of model outputs. It is expedient to combine both advantages of human experts and the computational capability of computers to create a tight-coupling incremental learning process for better performance. In this study, we develop RLTIR, an interactive identity recognition approach based on reinforcement learning, to adjust the identification model by human guidance. We first build a base tree-structured identity recognition model. And an expert is introduced in the model for giving feedback upon model outputs. Then, the model is updated according to strategies that are automatically learned under a designated reinforcement learning framework. To the best of our knowledge, it is the very first attempt to combine human expert knowledge with model learning in the area of identity recognition. The experimental results show that the reinforced interactive identity recognition framework outperforms baseline methods with regard to recognition accuracy and robustness.

A multistage approach to passive islanding detection is proposed that utilizes a decision-tree-like classification algorithm. The novelty of the proposed method is centered on the way in which features are passed to subsequent stages of the decision tree (DT). Feature sets extracted using different sized time windows are passed to successive stages of the tree. This provides two important advantages: (i) cases which can be easily determined as either islanding or non-islanding events are flagged as soon as possible without waiting for the full feature set to become available (ii) because the algorithm allows for the use of different sized time windows, features are analyzed in time-scales which fit their natural patterns of temporal evolution. The proposed classifier is trained and tested using a database of feature vectors, obtained using PSCAD, which were designed to reflect a variety of commonly encountered events on an IEEE 34-bus distribution system. One of the key requirements for the proposed algorithm was that easy cases should be flagged as soon as possible; this property was confirmed by the observation that most events (79%) were detected within 10-20ms, while at the same time retaining a very high detection rate overall cases (> 99%).

In view of most current studies on text sentiment classification focus on the deep learning model to obtain the sentimental characteristics of English text. Chinese text sentiment analysis is rarely involved, and only the context information of the statement is considered, but the syntax information of the statement is rarely considered. In this paper, a novel sentiment classification model is proposed (Dependency Tree Graph Convolutional Network, DTGCN) combined Chinese syntactically dependent tree with graph convolution. Firstly, the Bi-GRU (Bi-directional Gated Recurrent Unit) model is used to learn the contextual feature representation of a given text. Secondly, the syntax-dependent tree structure of a given text is constructed, then obtain its adjacency matrix according to the syntax-dependent tree, with the initial features extracted from the bidirectional gate control network, input into the graph convolutional neural network (GCN) to extract the sentimental features of the text; the obtained sentimental characteristics are then input into the classifier SoftMax for text sentimental polarity classification. Finally, the data set is compared with the mainstream neural network model. The experimental results show that the accuracy of the proposed DTGCN model proposed on the data set is 90.51% and the recall rate is 90.34%. Compared with the benchmark models (LSTM, CNN, TextCNN and Bi-GRU), the proposed DTGCN model shows a 4.45% advantage in accuracy. It shows that the proposed DTGCN model can effectively use the grammatical information of Chinese text to mine the hidden relationship in statements, it can improve the accuracy of Chinese text sentiment classification. In addition, the proposed DTGCN model not only improves the performance of sentiment classification in the essay, it also provides a new research method for social network public opinion identification.

Set similarity search, aiming to search the similar sets to a query set, has wide application in today's recommendation services. Meanwhile, the rapid advance in cloud technique has promoted the boom of data outsourcing. However, since the cloud is not fully trustable and the data may be sensitive, data should be encrypted before outsourced to the cloud. Undoubtedly, data encryption will hinder some basic functionalities, e.g., set similarity search. For achieving set similarity search over encrypted data, many solutions were proposed, yet they either only satisfy weak security requirements, or only achieve approximate similarity, or have low efficiency. Therefore, in this paper, we propose a new efficient and privacy-preserving exact set similarity search scheme. Specifically, we first design a symmetric-key predicate encryption (SPE-Sim) scheme, which can support similarity search over binary vectors. Then, we represent the set records to be binary vectors and employ the B+ tree to build an index for them. After that, based on SPE-Sim and the B+ tree based index, we propose our scheme and it can achieve efficient set similarity search while preserving the privacy of set records and query contents. Finally, security analysis and performance evaluation indicate that our scheme is privacy-preserving and efficient.

We propose a novel statistical approach to evaluate the statistical significance (reliability) of the results from discriminative sub-trajectory mining, which we call Statistically Discriminative Sub-trajectory Mining (Stat-DSM). Given two groups of trajectories, the goal of Stat-DSM is to extract moving patterns in the form of sub-trajectories that occur statistically significantly more often in one group than in the other. An advantage of the proposed method is that the statistical significance of the extracted sub-trajectories are properly controlled in the sense that the probability of finding a false discriminative sub-trajectory is smaller than a specified significance threshold α(e.g. 0.05), which is crucial when the method is used in scientific or social science studies under noisy environments. Finding such statistically discriminative sub-trajectories from a massive trajectory dataset is both computationally and statistically challenging. In the Stat-DSM method, we address these difficulties by introducing a tree representation of sub-trajectories, and applying a permutation-based statistical inference method to the tree. To the best of our knowledge, Stat-DSM is the first method that provides a statistical approach to quantify the reliability of discriminative sub-trajectory mining results. We illustrate the effectiveness and scalability of the Stat-DSM method by applying it to a real-world dataset containing 1,000,000 trajectories.

A practical min-sum algorithm is associated with tree-based comparison units for the check-node operation, being a major bottleneck in designing low-cost and energy-efficient low-density parity-check (LDPC) decoders. In this paper, we present a cost-effective LDPC decoder architecture by changing its internal computing resolution for the power-hungry check-node processing. The proposed mixed-resolution comparison offers significant advantages in terms of both area and energy, while achieving error-correcting performance within 0.3 dB of the previous normalized min-sum (NMS) algorithm for a (1644, 1408) quasi-cyclic LDPC code of the 5G New Radio specifications. Compared to the baseline NMS architecture, the proposed decoder in a 65-nm CMOS technology reduces the hardware complexity and the power consumption by 28.4% and 23.1%, respectively, enhancing the area efficiency by more than 88.2%.

The emergence of the financial supply chain provides assistance for small, medium and micro enterprises in the supply chain through a secured credit model based on real trade. Moreover, in the multi-level structure of the financial supply chain of the Internet of Things enterprise, there are information barriers and information islands. Besides, data is often not transmitted smoothly, and the intermediate offline process is complicated. What is worse, the efficiency is low, and the verification cost is high. Therefore, based on supply chain finance, an evolutionary risk model is constructed in this paper. Firstly, the income matrix of the regulatory risk model is established, and the convolutional neural network used will pool the training data to the maximum and set the local corresponding normalization layer. With the help of the evolutionary risk theory, the dynamic equation of the financial supply chain is obtained, forming the dynamic path and abnormal model of strategy selection. Then, a compact pattern tree is added to the knowledge granularity method to mine data anomalies. Finally, an experimental platform is built to verify the effectiveness of the method proposed in this paper, and experiments are performed on the accuracy of model evolution conditions, abnormal data identification, and abnormal numerical examples. The experimental results prove that the algorithm in this paper is consistent with the set parameters, and the effect is significantly higher than other comparison methods. The experimental mining time and the comparison method are shortened by 6 ∼ 13S. The research results obtained from this paper solve the problem that the decision-making of supply chain finance and the supervision and review of supply chain enterprise are complex, which improves the characteristics identification of supply chain platform, and provides reference suggestions for financial institutions and supply chain platforms.

This study explores urban forestry as a maintenance practice capable of enhancing more-than-human commons in the city. Focusing on the places associated with tree care, the methodology takes as a case study the Tokyo Metropolitan Parks, conducting quantitative and qualitative analysis through the means of immersive field work and questionnaires, to reveal how urban forestry practices materialize within the parks. Regarding the spatial relations between humans and/or non-humans with resources, different Urban Forestry Elements (UFE) have been found, as well as their collection in groups within the parks forming Urban Forestry Assemblages (UFA). The paper creates a comprehensive framework that reveals these places for urban forestry as important beacons for urban commoning.

Sentiment analysis on large data has become challenging due to the diversity, and nature of data. Advancements in the internet, along with large data availability have obviated the traditional limitations to distributed computing. The objective of this work is to carry out sentiment analysis on Apache Spark distributed Framework to speed up computations and enhance machine performance in diverse environments. The analysis, such as polarity identification, subjective analysis and email spam etc., are carried on various text datasets. After pre-processing, Term Frequency-Inverse Document Frequency (TF-IDF) and unsupervised Spark-Latent Dirichlet Allocation (LDA) clustering algorithms are used for feature extraction and selection to improve the accuracy. Deep Neural Networks (DNN), Support Vector Machines (SVM), Tree ensemble classifiers are used to evaluate the performance of the framework on single node and cluster environments. Finally, the proposed work aims at building an approach for enhancing machine performance, more in terms of runtime over accuracy.

Individual tree detection is critical for forest investigation and monitoring. Several existing methods have difficulties to detect trees in complex forest environment due to insufficiently mining descriptive features. This study proposes a deep learning framework based on a designed multi-channel information complementarity representation for detecting trees in complex forest using UAV laser scanning point clouds. The proposed method consists of two main stages: ground filtering and tree detection. In first stage, a modified graph convolution network with a local topological information layer is designed to separate the ground points. Unlike most existing parametric methods, our ground filtering method avoids the optimal parameters selection to adapt to different kinds of environments. For tree detection, a topdown slice (TDS) module is firstly designed to mine the vertical structure information in a top-down way. Then, a special multichannel representation (MCR) is developed to perserve different distribution patterns of points from complementary perspectives. Finally, a multi-branch network (MBNet) is proposed for individual tree detection by fusing multi-channel features, which can provide discriminative information for MBNet to detect trees more accurately. MBNet was evaluated on seven forest areas (UAV LiDAR data with the mean size of 14,000 m2 and point density of 250 points/m2). Experimental results showed that the proposed framework achieves excellent performance. Our method obtains promising performance with mean recall of 89.23% and mean F1-score of 87.04%.

In large-scale industrial applications, goods must be continuously transported between locations, which in the absence of conveyor systems is by a fleet of individual vehicles. This article introduces flow-achieving scheduling tree (FAST), an online dispatching algorithm that allows vehicles to efficiently operate as a team to maximize the system's throughput while meeting a production schedule. A high-performance model is developed for high-fidelity prediction of vehicle interactions and system performance. It is subsequently optimized using a self-tuning variant of Monte Carlo tree search (MCTS) to make agile dispatch decisions in real time. The method is validated using an open-cut mine site and is shown to outperform a commonly used algorithm in this domain. Note to Practitioners - This article was motivated by the problem of dispatching autonomous haul trucks on open-cut mine sites. The proposed method is suited to any industrial transportation system where a continuous stream of goods must be efficiently transported between the load and unload stations by a potentially heterogeneous fleet of automated vehicles. The system makes decisions in real time while reacting to performance variations and disturbances by using a receding horizon approach. Off-the-shelf software commonly used in this domain is based on heuristics with limited ability to optimize, leading to myopic decision making without taking vehicle interactions into account. Here, flow-achieving scheduling tree (FAST) overcomes this by optimizing over possible schedules and thereby implicitly accounting for knock-on effects. Future work will incorporate additional constraints into the optimization process and validate FAST in other industrial domains.

Social networking sites in the most modernized world are flooded with large data volumes. Extracting the sentiment polarity of important aspects is necessary;as it helps to determine people’s opinions through what they write. The Coronavirus pandemic has invaded the world and been given a mention in the social media on a large scale. In a very short period of time, tweets indicate unpredicted increase of coronavirus. They reflect people’s opinions and thoughts with regard to coronavirus and its impact on society. The research community has been interested in discovering the hidden relationships from short texts such as Twitter and Weiboa;due to their shortness and sparsity. In this paper, a hierarchical twitter sentiment model (HTSM) is proposed to show people’s opinions in short texts. The proposed HTSM has two main features as follows: constructing a hierarchical tree of important aspects from short texts without a predefined hierarchy depth and width, as well as analyzing the extracted opinions to discover the sentiment polarity on those important aspects by applying a valence aware dictionary for sentiment reasoner (VADER) sentiment analysis. The tweets for each extracted important aspect can be categorized as follows: strongly positive, positive, neutral, strongly negative, or negative. The quality of the proposed model is validated by applying it to a popular product and a widespread topic. The results show that the proposed model outperforms the state-of-the-art methods used in analyzing people’s opinions in short text effectively.

When the images are captured by drones, the effect of oblique angles, distance variations and open environment are the main challenges for successful palm tree detection. This paper presents a method towards palm tree counting in Drone images using a novel idea of detecting dominant points by exploring Generalized Gradient Vector Flow, which defines symmetry based on gradient direction of the pixels. For each dominant point, we use angle information for classifying diagonal dominant points. It is intuition that the direction of the branches of tree converges at center of tree irrespective of the type of tree and plants. This observation motivated us to expand the direction of diagonal dominant points until it finds intersection point with another diagonal dominant point and this results in candidate points. For each candidate point, the proposed method constructs the ring by considering the distance between the intersection point and nearest neighbor candidate point as radius. This outputs region of interest and it includes center of each tree in the image. To ease the effect of complex background, we explore YOLOv5 architecture to remove false region of interests. This step results in counting oil palm trees in the mages irrespective of tree type of palm family. Experimental results on our dataset of the images captured by drones and standard dataset of coconut images captured by unmanned aerial vehicle of different trees show that the proposed method is effective and performs better than SOTA methods.