Extraction Approach Research Articles

Fundamental Frequency Extraction by Utilizing Accumulated Power Spectrum based Weighted Autocorrelation Function in Noisy Speech

This research suggests an efficient idea that is better suited for speech processing applications for retrieving the accurate pitch from speech signal in noisy conditions. For this objective, we present a fundamental frequency extraction algorithm and that is tolerant to the non-stationary changes of the amplitude and frequency of the input signal. Moreover, we use an accumulated power spectrum instead of power spectrum, which uses the shorter sub-frames of the input signal to reduce the noise characteristics of the speech signals. To increase the accuracy of the fundamental frequency extraction we have concentrated on maintaining the speech harmonics in their original state and suppressing the noise elements involved in the noisy speech signal. The two stages that make up the suggested fundamental frequency extraction approach are producing the accumulated power spectrum of the speech signal and weighting it with the average magnitude difference function. As per the experiment results, the proposed technique appears to be better in noisy situations than other existing state-of-the-art methods such as Weighted Autocorrelation Function (WAF), PEFAC, and BaNa.

Tracking dynamics characteristics of tidal flats using landsat time series and Google Earth Engine cloud platform

Tidal flats serve as vital spatial resources within coastal wetlands and play crucial roles in biological habitat preservation, environmental conservation, and human development. However, accurately delineating their extent from instantaneous remote sensing images poses challenges, owing to the dynamic interplay between seawater and land. Therefore, this study utilized the consistency of remote sensing satellites and developed a multi-feature decision approach based on the long-term remote sensing datasets and the Google Earth Engine (GEE) cloud platform for determining the spatial extent, classifying types, and mapping the spatial-temporal distribution of the tidal flats. Initially, a multi-temporal image stack was compiled from the filtered remote sensing images. Subsequently, the modified normalized difference water index (MNDWI) and automated water extraction index (AWEI) were calculated to establish the maximum and minimum water surfaces using the extreme value composite algorithm (EVCA). The Otsu algorithm and spatial overlay analysis method were then utilized to accurately delineate the spatial extent of the tidal flats. Additionally, the Normalized Difference Vegetation Index (NDVI) was utilized to accurately identify tidal flat types. Post-processing involves elevation data and mathematical morphological methods to mitigate the impact of permanent water bodies. Finally, the accuracy of the extracted spatial extent and types of tidal flats was evaluated. The efficacy and practicality of the proposed method were validated using the Zhoushan Archipelago and Landsat time series in China. The results revealed the following: (1) the acquired tidal flat information exhibited evident boundaries and accurate types, achieving an overall accuracy (OA) of 94.80 % and a Kappa coefficient of 0.89; (2) the area of tidal flats in the Zhoushan Archipelago increased from 2,182.19 ha in 1985 to 3,761.21 ha in 2020, with an average annual increase of 45.12 ha and an average annual increase rate of 1.57 %; and (3) over 35 periods, the area transformed from other land types to tidal flats amounted to 2,895.74 ha, while the area converted from tidal flats to other land types totaled 1,651.90 ha. The three islands with the most rapid growth in tidal flat area were Liuheng Island, Dachangtu Island, and Daishan Island, with changes of 675.68 ha, 380.47 ha, and 362.63 ha, respectively. This method can offer an automated, swift, and accurate approach for tidal flat extraction, demonstrating high precision and practical effectiveness, thereby providing robust technical support for coastal resource surveys.

A Deep-Based Approach for Multi-Descriptor Feature Extraction: Applications on SAR Image Registration

Synthetic aperture radar (SAR) images have found increasing attention in various applications, such as remote sensing, surveillance, and disaster management. Unlike optical sensors, SAR can capture images in any weather conditions at any time, making it particularly valuable. However, it poses unique challenges for image processing tasks, like complex speckle noise, texture, and geometric distortions. For many image processing tasks such as image registration; feature detection and extraction are critical initial steps. In this work, we propose a deep learning-based method for detecting and describing keypoints in SAR images, which can be specifically applied to SAR image registration tasks. To address the challenges of SAR images, we utilize the R2D2 network and propose a training scheme specifically tailored for these images. Furthermore, our approach involves multiple descriptors utilization for outlier removal between image keypoints and a two-stage pipeline consisting of coarse and fine stages for robust feature point matching of SAR images. By leveraging the coarse registration stage, which maintains robustness, and also a fine stage that employs multiple descriptors along with a local search technique, our approach enhances the keypoint matching accuracy. Evaluation results show that the proposed method outperforms most of the traditional and deep learning-based methods in terms of the percentage of correct matches, while achieving comparable or even better root mean squared error (RMSE) results.

Computer-Aided Detection and Diagnosis of Breast Cancer: a Review

Statistics across different countries point to breast cancer being among severe cancers with a high mortality rate. Early detection is essential when it comes to reducing the severity and mortality of breast cancer. Researchers proposed many computer-aided diagnosis/detection (CAD) techniques for this purpose. Many perform well (over 90% of classification accuracy, sensitivity, specificity, and f-1 sore), nevertheless, there is still room for improvement. This paper reviews literature related to breast cancer and the challenges faced by the research community. It discusses the common stages of breast cancer detection/ diagnosis using CAD models along with deep learning and transfer learning (TL) methods. In recent studies, deep learning models outperformed the handcrafted feature extraction and classification task and the semantic segmentation of ROI images achieved good results. An accuracy of up to 99.8% has been obtained using these techniques. Furthermore, using TL, researchers combine the power of both, pre-trained deep learning-based networks and traditional feature extraction approaches.

Use of Zero-Valent Iron Nanoparticles (nZVIs) from Environmentally Friendly Synthesis for the Removal of Dyes from Water—A Review

This review article addresses the increasing environmental concerns posed by synthetic dyes in water, exploring innovative approaches for their removal with a focus on zero-valent iron nanoparticles (nZVIs) synthesized through environmentally friendly methods. The article begins by highlighting the persistent nature of synthetic dyes and the limitations of conventional degradation processes. The role of nanoparticles in environmental applications is then discussed, covering diverse methods for metallic nanoparticle production aligned with green chemistry principles. Various methods, including the incorporation of secondary metals, surface coating, emulsification, fixed support, encapsulation, and electrostatic stabilization, are detailed in relation to the stabilization of nZVIs. A novel aspect is introduced in the use of plant extract or biomimetic approaches for chemical reduction during nZVI synthesis. The review investigates the specific challenges posed by dye pollution in wastewater from industrial sources, particularly in the context of garment coloring. Current approaches for dye removal in aqueous environments are discussed, with an emphasis on the effectiveness of green-synthesized nZVIs. The article concludes by offering insights into future perspectives and challenges in the field. The intricate landscape of environmentally friendly nZVI synthesis has been presented, showcasing its potential as a sustainable solution for addressing dye pollution in water.

Janus structured photothermal conversion materials prepared from carbonized corn straw particles for portable air water extraction devices

The utilization of photothermal conversion materials to enhance the desorption performance of hygroscopic salt solutions through interfacial photothermal effects presents a promising approach for the continuous extraction of water from the atmosphere. To improve the desorption efficiency of hygroscopic salt solutions, the objective of this research is to employ agricultural and forestry residues, such as corn straw, in conjunction with polyurethane sponges, for the production of an innovative Janus structure carbonized biomass photothermal conversion material. Compared to single-layer structured photothermal conversion materials, the pure water evaporation rate increased from 2.42 kg m-2 h-1 to 3.20 kg m-2 h-1 when utilizing the Janus structured photothermal conversion material. Remarkably, this material demonstrates outstanding resistance to salt, allowing it to endure 8 h evaporation cycles with 30 wt% NaCl without salt crystallization. Therefore, it is well-suited for the continuous desorption of liquid hygroscopic agents. Moreover, the portable air–water extraction device, which incorporates Janus structural photothermal conversion material to enhance the performance of 30 % LiCl, has been shown to effectively extract water in practical settings. It achieves a water intake rate of 1.74 L m-2 d-1 at 50 % humidity. This approach is distinguished by its simplicity, cost-effectiveness, and efficient utilization of solar energy resources, providing a promising solution to mitigate the shortage of fresh water resources.

Understanding remote sensing imagery like reading a text document: What can remote sensing image captioning offer?

Remote sensing imagery offers intricate and nuanced data, emphasizing the need for a profound understanding of the relationships among varied geographical elements and events. In this study, we explore the transitions from the image domain to the text domain by employing four state-of-the-art image captioning algorithms, i.e., BLIP, mPLUG, OFA, and X-VLM. Specifically, we investigate (1) the stability of these image captioning algorithms for remote sensing image captioning, (2) the preservation of similarity between images and their corresponding captions, and (3) the characteristics of their caption embedding spaces. The results suggest a moderate consistency across generated captions from different image captioning models, with observable variations contingent upon the urban entities presented. In addition, a dynamic relationship emerges between image space and the corresponding caption space, evidenced by their fluctuated correlation coefficient. Most importantly, patterns within the caption embedding space align with the observed land cover and land use in the image patches, reaffirming the potential of our pilot work as an impactful analytical approach in future remote sensing analytics. We advocate that integrating image captioning techniques with remote sensing imagery paves the way for an innovative data extraction and interpretation approach with diverse applications.

Topics in the Haystack: Enhancing Topic Quality through Corpus Expansion

Abstract Extracting and identifying latent topics in large text corpora have gained increasing importance in Natural Language Processing (NLP). Most models, whether probabilistic models similar to Latent Dirichlet Allocation (LDA) or neural topic models, follow the same underlying approach of topic interpretability and topic extraction. We propose a method that incorporates a deeper understanding of both sentence and document themes, and goes beyond simply analyzing word frequencies in the data. Through simple corpus expansion, our model can detect latent topics that may include uncommon words or neologisms, as well as words not present in the documents themselves. Additionally, we propose several new evaluation metrics based on intruder words and similarity measures in the semantic space. We present correlation coefficients with human identification of intruder words and achieve near-human level results at the word-intrusion task. We demonstrate the competitive performance of our method with a large benchmark study, and achieve superior results compared with state-of-the-art topic modeling and document clustering models. The code is available at the following link: https://github.com/AnFreTh/STREAM.

Preliminary study for Polycyclic aromatic Hydrocarbons mobilization from contaminated marine sediment using synthetic and natural surfactants

The persistent presence of Polycyclic Aromatic Hydrocarbons (PAHs) in soils and sediments due to their chemical properties requires new methods to mobilize and make them more available for remediation purposes. In this work, the evaluation of the abilities of eight different non-ionic sugar-based and totally biodegradable surfactants, such as synthetic alkyl polyglycosides (APGs), biological sophorolipids (SLs) and biological rhamnolipids (RLs), was conducted in order to provide a preliminary guideline for the selection of the surfactant and the technical approach for PAHs extraction from the sediment. The reference sample was a marine sediment collected from Bagnoli (Naples, Italy) that was characterized to evaluate the level of PAHs contamination, which resulted equal to 3.51 g Kg−1 of total PAHs in the sediment. By using surfactants solutions with a surfactant concentration five times greater than critical micelle concentration (Cs = 5x CMC), a preliminary washing test in batch configuration was conducted, then followed by multiple consecutive washes (MCW) of the sediment to assess the solubilization of PAHs from the sediment by the action of selected surfactants. The results show an evident advantage given by the employment of each studied surfactant in mobilizing PAHs, compared to distilled water as benchmark. In detail, the synthetic alkyl polyglycosides APG2 led to a 3.4 % of total PAHs mobilization in the preliminary washing test with a maximum peak of 9.8 % for a single compound. The MCW test demonstrates that more consecutive washes can increase the amount of total PAHs removed, with a similar contribution from each wash, and that biosurfactants can be more attractive after several washes thanks to the increased capacity of PAHs mobilization. Interestingly, the high efficiency of surfactant to mobilize PAHs makes the soil washing a more attractive technology for removing PAHs from the marine sediments.

Optimization of intelligent guided vehicle vision navigation based on improved YOLOv2.

Addressing the challenge of limited accuracy and real-time performance in intelligent guided vehicle (IGV) image recognition and detection, typically reliant on traditional feature extraction approaches. This study delves into a visual navigation detection method using an improved You Only Look Once (YOLO) model-simplified YOLOv2 (SYOLOv2) to satisfy the complex operating conditions of the port and the limitations of IGV hardware computing. The convolutional neural network structure of YOLOv2 is refined to ensure adaptability to varying weather conditions using a single image. Preprocessing of images involves Contrast Limited Adaptive Histogram Equalization (CLAHE), while an adaptive image resolution detection model, contingent upon vehicle speed, is proposed to enhance the detection performance. The comparative experiments conducted on image datasets reflective of actual road conditions and weather conditions demonstrate notable enhancements in accuracy and frames transmitted per second compared to conventional methods. These improvements signify the efficacy of the proposed approach in meeting the stringent requirements for real-time detection on IGV platforms.

Structural Transformation Through a Multi-vector Geo-economic Governance? BRI and Upgrading of the Uzbek Gas Industry

Gas is a strategic source of energy and Uzbekistan ranks 11th in the world for mining and 14th for reserves. The article investigates whether and how the BRI and Chinese capital have contributed to Uzbek structural transformation in the gas industry. It argues that although the Chinese BRI seems to adopt an extractive approach to acquire natural resources, its interventions are also an opportunity for multi-directional forms of upgrading in the gas sector, both directly and indirectly. Directly, first the Chinese involvement as a consumer has reconfigured geo-economic power relations around gas. Secondly, there is an unprecedented support by China to national infrastructure development, both as a lender and a producer. Thirdly, China is the main source of machineries to enable energy transmission. Despite these factors, BRI and the Chinese presence are contributing only marginally to upgrading. A coordinated industrial strategy coming from the Uzbek state remains a necessary condition for structural transformation.

Multimodal Geo-Information Extraction from Social Media for Supporting Decision-Making in Disaster Management

Abstract. Effective decision-making in natural disaster management relies heavily on a comprehensive understanding of the situation in affected areas. Social media has been established as a tool to monitor human response and damage assessment. Given the vast amounts of data available, computational methods such as topic modelling are typically employed to reduce information complexity. However, these methods mostly neglect aspects such as geographic location and emotional response, which frequently results in sequential workflows of initial semantic filtering and subsequent spatial or spatio-temporal analysis. This study presents a novel approach for multimodal information extraction from geo-social media data for aiding decision support in disaster management. The method leverages a spatial, temporal, semantic, and sentiment-based clustering approach of social media posts to extract clusters that provide insights into disaster-related content. A case study in the Ahr Valley region in Germany demonstrates the method’s effectiveness in providing actionable insights for disaster response and management. The approach offers a tool for the quick assessment of disaster-related information from social media, potentially aiding timely and informed decision-making.

Environmentally Friendly Processing of Forestry Biomass Side Streams – Coniferous Needles and Greenery

Replacement of fossil materials with renewable biomass is essential to address climate change challenges and implement bioeconomy as essential element of sustainable development model. A significant source of biomass is forestry, however besides timber significant amounts of forestry biomass side streams are formed and from circular bioeconomy perspective full utilisation of valuable resources is requested. One of side products of coniferous tree processing are needles and greenery and as these trees are dominant in Northern regions full use of their biomass can provide significant input to replace fossil resource-based substances and materials. Coniferous tree needles and greenery are a rich source of biologically active substances with wide application potential as resource for biopharma industries, for food and feed supplements and materials for diverse application. Traditionally for extraction of biologically active substances from coniferous needles and greenery toxic and hazardous solvents, such as organochlorine and hydrocarbon solvents has been used. The aim of the present study is to develop possibilities to use green chemistry approaches for coniferous needle and greenery extraction and following biorefinery to obtain biologically active components. For extraction of coniferous needle and greenery green solvents has been tested as well as so called intensive extraction methos has been used. The yield of extracts depends on extraction temperature, duration, solvent and other factors and optimal extraction conditions provide possibilities to obtain yield of extracts higher that use of traditionally used solvents. As a powerful tool to increase yields of extracts so called intensive extraction methods, such as treatment with ultrasound, microwaves, accelerated solvent extraction has been studied. The obtained extracts were characterised using gas chromatography with mass spectrometric detection, liquid chromatography and other methods. Possibilities of biorefinery of obtained extracts to isolate groups of substances or individual substances has been discussed.

Fine-resolution estimation for urban surface water pollution susceptibility with multi-modal earth observation data

The sustainability and suitability of water resources are of great importance for maintaining urban populations. The landscapes and environment around urban waters have always been the main focus of maintaining water quality for sustainable water supplies. Early-stage field investigations recognized the influence of land use/land cover (LULC) on water quality. To extend the research scope in spatial and temporal dimensions, remote sensing techniques have been utilized to discover the relationships between LULC and water quality. However, these remote sensing datasets generally had a medium spatial resolution, making them unable to support the fine-detailed land classifications that are critical to explore the water quality in an urban area. Moreover, although more details regarding the land surface are available from the currently-generated high-resolution and very-high-resolution remote sensing images, this land surface information is too complex for the state-of-the-art deep learning approaches and benchmark datasets. This manuscript reports our efforts on developing a framework to explore the fine-resolution relationship between surface water pollution and LULC. To address the cost of computing time and limitations of well-labelled datasets, we employ a foundation model-enhanced approach for water extraction and water-surrounded LULC classification. We propose an estimator of surface water pollution susceptibility to main pollutants based on the surrounding LULCs. Selecting the Future City of Beijing as the study area, based on very-high-resolution remote sensing images, the experiment proved that our proposed approach could effectively map the susceptibility of surface water pollution caused by its surrounding land use and land cover. To our knowledge, the relationship of LULCs and water quality have not been investigated using 0.5 m spatial resolution data. We hope our work can provide a prospective fine-detailed water quality analysis in the community of water environment of remote sensing.

Unsupervised literature mining approaches for extracting relationships pertaining to habitats and reproductive conditions of plant species

IntroductionFine-grained, descriptive information on habitats and reproductive conditions of plant species are crucial in forest restoration and rehabilitation efforts. Precise timing of fruit collection and knowledge of species' habitat preferences and reproductive status are necessary especially for tropical plant species that have short-lived recalcitrant seeds, and those that exhibit complex reproductive patterns, e.g., species with supra-annual mass flowering events that may occur in irregular intervals. Understanding plant regeneration in the way of planning for effective reforestation can be aided by providing access to structured information, e.g., in knowledge bases, that spans years if not decades as well as covering a wide range of geographic locations. The content of such a resource can be enriched with literature-derived information on species' time-sensitive reproductive conditions and location-specific habitats.MethodsWe sought to develop unsupervised approaches to extract relationships pertaining to habitats and their locations, and reproductive conditions of plant species and corresponding temporal information. Firstly, we handcrafted rules for a traditional rule-based pattern matching approach. We then developed a relation extraction approach building upon transformer models, i.e., the Text-to-Text Transfer Transformer (T5), casting the relation extraction problem as a question answering and natural language inference task. We then propose a novel unsupervised hybrid approach that combines our rule-based and transformer-based approaches.ResultsEvaluation of our hybrid approach on an annotated corpus of biodiversity-focused documents demonstrated an improvement of up to 15 percentage points in recall and best performance over solely rule-based and transformer-based methods with F1-scores ranging from 89.61 to 96.75% for reproductive condition - temporal expression relations, and ranging from 85.39% to 89.90% for habitat - geographic location relations. Our work shows that even without training models on any domain-specific labeled dataset, we are able to extract relationships between biodiversity concepts from literature with satisfactory performance.

FP-GCN: Frequency Pyramid Graph Convolutional Network for Enhancing Pathological Gait Classification.

Gait, a manifestation of one's walking pattern, intricately reflects the harmonious interplay of various bodily systems, offering valuable insights into an individual's health status. However, the current study has shortcomings in the extraction of temporal and spatial dependencies in joint motion, resulting in inefficiencies in pathological gait classification. In this paper, we propose a Frequency Pyramid Graph Convolutional Network (FP-GCN), advocating to complement temporal analysis and further enhance spatial feature extraction. specifically, a spectral decomposition component is adopted to extract gait data with different time frames, which can enhance the detection of rhythmic patterns and velocity variations in human gait and allow a detailed analysis of the temporal features. Furthermore, a novel pyramidal feature extraction approach is developed to analyze the inter-sensor dependencies, which can integrate features from different pathways, enhancing both temporal and spatial feature extraction. Our experimentation on diverse datasets demonstrates the effectiveness of our approach. Notably, FP-GCN achieves an impressive accuracy of 98.78% on public datasets and 96.54% on proprietary data, surpassing existing methodologies and underscoring its potential for advancing pathological gait classification. In summary, our innovative FP-GCN contributes to advancing feature extraction and pathological gait recognition, which may offer potential advancements in healthcare provisions, especially in regions with limited access to medical resources and in home-care environments. This work lays the foundation for further exploration and underscores the importance of remote health monitoring, diagnosis, and personalized interventions.

Development of a NiFe2O4 covalent organic framework based magnetic solid-phase extraction approach for specific capture of quinolones in animal innards prior to UHPLC–Q–Orbitrap HRMS detection

This study aimed to present a selective and effective method for analyzing quinolones (QNs) in food matrix. Herein, a NiFe2O4-based magnetic sodium disulfonate covalent organic framework (NiFe2O4/COF) was prepared using a simple solvent-free grinding method, and was adopted as a selective adsorbent for magnetic solid phase extraction of QNs. Coupled with UHPLC–Q–Orbitrap HRMS, an efficient method for simultaneous detection of 18 kinds of QNs was established. The method exhibited good linearity (0.01–100 ng g−1), high sensitivity (LODs ranging from 0.0011 to 0.0652 ng g−1) and precision (RSDs below 9.5%). Successful extraction of QNs from liver and kidney samples was achieved with satisfactory recoveries ranging from 82.2% to 108.4%. The abundant sulfonate functional groups on NiFe2O4/COF facilitated strong affinity to QNs through electrostatic and hydrogen bonding interactions. The proposed method provides a new idea for the extraction of contaminants with target selectivity.

A deep learning based approach for image retrieval extraction in mobile edge computing

AbstractDeep learning has been widely explored in 5G applications, including computer vision, the Internet of Things (IoT), and intermedia classification. However, applying the deep learning approach in limited-resource mobile devices is one of the most challenging issues. At the same time, users’ experience in terms of Quality of Service (QoS) (e.g., service latency, outcome accuracy, and achievable data rate) performs poorly while interacting with machine learning applications. Mobile edge computing (MEC) has been introduced as a cooperative approach to bring computation resources in proximity to end-user devices to overcome these limitations. This article aims to design a novel image reiterative extraction algorithm based on convolution neural network (CNN) learning and computational task offloading to support machine learning-based mobile applications in resource-limited and uncertain environments. Accordingly, we leverage the framework of image retrieval extraction and introduce three approaches. First, privacy preservation is strict and aims to protect personal data. Second, network traffic reduction. Third, minimizing feature matching time. Our simulation results associated with real-time experiments on a small-scale MEC server have shown the effectiveness of the proposed deep learning-based approach over existing schemes. The source code is available here: https://github.com/jamalalasadi/CNN_Image_retrieval.

Towards a regenerative shift in tourism: applying a regenerative conceptual framework toward swimmable urban rivers

Regenerative tourism is a transformational approach to healing relationships between tourism, places and communities. Several urban rivers are being made swimmable (again) to mitigate against negative climate effects, promote urban health and liveability and contribute to the city’s tourism potential. This paper examines the application of a regenerative tourism conceptual framework (RTCF) to the Swimmable Birrarung/Yarra River (SB2030) initiative in Narrm, Melbourne, Australia and the dynamics among the key initiative stakeholders. Swimming is applied to catalyse regenerative transformations of the city’s main waterway. Tourism’s contributions to regenerating the river and its community are examined. The RTCF is tested for the development and implementation of a transdisciplinary action research project involving the river, civil society, academic, Indigenous, business, and government actors. Analysis of the SB2030 initiative shows that extractive approaches dominate tourism’s approach to the river but also that tourism can play a critical role in supporting the regenerative development of the river and its community. Rather than a type of tourism, it positions tourism’s core purpose as a contributor to the regeneration of social-ecological systems. Evidently, other sectors must create conditions suitable for tourism to support the multi-systems urban river regeneration impetus. This paper contributes to the discursive developments of regenerative tourism applications and informs urban regenerative development transformations.

Explainability of three-dimensional convolutional neural networks for functional magnetic resonance imaging of Alzheimer's disease classification based on gradient-weighted class activation mapping.

Currently, numerous studies focus on employing fMRI-based deep neural networks to diagnose neurological disorders such as Alzheimer's Disease (AD), yet only a handful have provided results regarding explainability. We address this gap by applying several prevalent explainability methods such as gradient-weighted class activation mapping (Grad-CAM) to an fMRI-based 3D-VGG16 network for AD diagnosis to improve the model's explainability. The aim is to explore the specific Region of Interest (ROI) of brain the model primarily focuses on when making predictions, as well as whether there are differences in these ROIs between AD and normal controls (NCs). First, we utilized multiple resting-state functional activity maps including ALFF, fALFF, ReHo, and VMHC to reduce the complexity of fMRI data, which differed from many studies that utilized raw fMRI data. Compared to methods utilizing raw fMRI data, this manual feature extraction approach may potentially alleviate the model's burden. Subsequently, 3D-VGG16 were employed for AD classification, where the final fully connected layers were replaced with a Global Average Pooling (GAP) layer, aimed at mitigating overfitting while preserving spatial information within the feature maps. The model achieved a maximum of 96.4% accuracy on the test set. Finally, several 3D CAM methods were employed to interpret the models. In the explainability results of the models with relatively high accuracy, the highlighted ROIs were primarily located in the precuneus and the hippocampus for AD subjects, while the models focused on the entire brain for NC. This supports current research on ROIs involved in AD. We believe that explaining deep learning models would not only provide support for existing research on brain disorders, but also offer important referential recommendations for the study of currently unknown etiologies.