Asif Aziz Memon

These days, The website Uniform Resource Locator (URL) is widely used for accessing and navigating online information. However, the rise of AI-generated fake content, scams, counterfeit URLs, and other cyberattacks has significantly increased phishing-related threats. These fake URLs are difficult to identify because phishing links often resemble legitimate URLs. Consequently, both known and unknown (zero-day) phishing attacks remain difficult to detect in practice.This paper presents a hybrid deep learning–based intrusion detection system capable of detecting both known and zero-day phishing URLs. The objective is to provide users with absolute URLs while protecting them from fake ones. Another goal is to design an adaptive intrusion detection system (IDS) that combines static analysis, signature-based detection, and heuristic methods to identify phishing URLs. The proposed method, named the Zero-Phishing Convolutional Neural Network and Long Short-Term Memory (ZP-CNN-LSTM) algorithm, consists of three distinct schemes. For instance, static analysis rules are based on regular expressions, signatures for convolutional neural networks (CNNs), and zero-day detection using LSTM and autoencoders. We tested our project in the VR and AR research laboratory on 2 million testbed URLs, determined whether they were real or fake with respect to phishing, and predicted their phishing patterns. Results show that the proposed method achieves 98% higher accuracy than existing phishing detection methods in practice.

Speech Emotion Recognition (SER) technology helps computers understand human emotions in speech, which fills a critical niche in advancing human–computer interaction and mental health diagnostics. The primary objective of this study is to enhance SER accuracy and generalization through innovative deep learning models. Despite its importance in various fields like human–computer interaction and mental health diagnosis, accurately identifying emotions from speech can be challenging due to differences in speakers, accents, and background noise. The work proposes two innovative deep learning models to improve SER accuracy: a CNN-LSTM model and an Attention-Enhanced CNN-LSTM model. These models were tested on the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), collected between 2015 and 2018, which comprises 1440 audio files of male and female actors expressing eight emotions. Both models achieved impressive accuracy rates of over 96% in classifying emotions into eight categories. By comparing the CNN-LSTM and Attention-Enhanced CNN-LSTM models, this study offers comparative insights into modeling techniques, contributes to the development of more effective emotion recognition systems, and offers practical implications for real-time applications in healthcare and customer service.

Image segmentation is a tedious task that suffers from constraints, such as blurred or weak edges and intensity inhomogeneity. Active contour models, including edge-based and region-based methods, are extensively used for image segmentation. Each of these methods has its pros and cons that affect image-segmentation accuracy and CPU processing time. This study combines local and global region-based fitting energies and uses statistical image information to drag contours toward object boundaries, thus overcoming image inhomogeneity. The bias field, the region affected by image artefacts, is calculated and added with the local fitting energy model to capture inhomogeneous object boundaries. Furthermore, the combined local and global statistical information is appended with the edge-indicator function to rapidly move the contour over objects with strong edges, thereby avoiding boundary leakage. A region-based length term is driven by the signed pressure force function that evolves the curve on either the outer or inner side of the object, depending on its sign. The signed pressure force function contributes to achieving a smoother version of energy minimization over gradient descent flow. The proposed active contour model is applied to multiple synthetically generated, and medical images, together with online available public databases: the PH ² database, the skin-cancer-mnist-ham10000 THUS10000 database and the specific images from PascalVOC2007 database [1]. All the experiments confirm the better segmentation accuracy and improved time potency of the proposed methodology over previous level set-based approaches.

This research presents hybrid level set evolution for complex and inhomogeneous image segmentation. Firstly, we develop an adaptive force with level set evolution, which is driven by region information. Adaptive force is produced by consolidating local and global force terms in an altered fashion. Besides, to avoid local fitting terms being stuck into a local minimum, we use the swap function to interchange the fitting terms so that fitting values inside the object are always higher. Later for the elimination of the costly contour initialization that existed in previous level set based evolutions, we integrate kernel based fuzzy c-means clustering and intensity-based thresholding framework with the proposed framework to automate the proposed strategy. Finally, for the level set function regularization and the for the elimination of its re-initialization we have used the Gaussian function in the level set evolution. We demonstrate the results on some complex images to show the strong and exact segmentation results that are conceivable with this new class of adaptive active contour model. We have additionally performed statistical analysis on real images and BRATS dataset using Dice index, accuracy, sensitivity, specificity and Jaccard index metrics. Results show that the proposed method gets high Dice index, accuracy, sensitivity, specificity and Jaccard index values compared to the previous state of art methods.

Fashion image analysis has attracted significant research attention owing to the availability of large-scale fashion datasets with rich annotations. However, existing deep learning models for fashion datasets often have high computational requirements. In this study, we propose a new model suitable for low-power devices. The proposed network is a one-stage detector that rapidly detects multiple cloths and landmarks in fashion images. The network is designed as a modification of the EfficientDet originally proposed by Google Brain. The proposed network simultaneously trains the core input features with different resolutions and applies compound scaling to the backbone feature network. The bounding box/class/landmark prediction networks maintain the balance between the speed and accuracy. Moreover, a low number of parameters and low computational cost make it efficient. Without image preprocessing, we achieved 0.686 mean average precision (mAP) in the bounding box detection and 0.450 mAP in the landmark estimation on the DeepFashion2 validation dataset with an inference time of 42 ms. We obtained optimal results in extensive experiments with loss functions and optimizers. Furthermore, the proposed method has the advantage of operating in low-power devices.

Active contour models have achieved prominent success in the area of image segmentation, allowing complex objects to be segmented from the background for further analysis. Existing models can be divided into region-based active contour models and edge-based active contour models. However, both models use direct image data to achieve segmentation and face many challenging problems in terms of the initial contour position, noise sensitivity, local minima and inefficiency owing to the in-homogeneity of image intensities. The saliency map of an image changes the image representation, making it more visual and meaningful. In this study, we propose a novel model that uses the advantages of a saliency map with local image information (LIF) and overcomes the drawbacks of previous models. The proposed model is driven by a saliency map of an image and the local image information to enhance the progress of the active contour models. In this model, the saliency map of an image is first computed to find the saliency driven local fitting energy. Then, the saliency-driven local fitting energy is combined with the LIF model, resulting in a final novel energy functional. This final energy functional is formulated through a level set formulation, and regulation terms are added to evolve the contour more precisely across the object boundaries. The quality of the proposed method was verified on different synthetic images, real images and publicly available datasets, including medical images. The image segmentation results, and quantitative comparisons confirmed the contour initialization independence, noise insensitivity, and superior segmentation accuracy of the proposed model in comparison to the other segmentation models.

Segmentation accuracy is an important criterion for evaluating the performance of segmentation techniques used to extract objects of interest from images, such as the active contour model. However, segmentation accuracy can be affected by image artifacts such as intensity inhomogeneity, which makes it difficult to extract objects with inhomogeneous intensities. To address this issue, this paper proposes a hybrid region-based active contour model for the segmentation of inhomogeneous images. The proposed hybrid energy functional combines local and global intensity functions; an incorporated weight function is parameterized based on local image contrast. The inclusion of this weight function smoothens the contours at different intensity level boundaries, thereby yielding improved segmentation. The weight function suppresses false contour evolution and also regularizes object boundaries. Compared with other state-of-the-art methods, the proposed approach achieves superior results over synthetic and real images. Based on a quantitative analysis over the mini-MIAS and PH² databases, the superiority of the proposed model in terms of segmentation accuracy, as compared with the ground truths, was confirmed. Furthermore, when using the proposed model, the processing time for image segmentation is lower than those when using other methods.

Image segmentation is a crucial stage of image analysis systems because it detects and extracts regions of interest for further processing, such as image recognition and the image description. However, segmenting images is not always easy because segmentation accuracy depends significantly on image characteristics, such as color, texture, and intensity. Image inhomogeneity profoundly degrades the segmentation performance of segmentation models. This article contributes to image segmentation literature by presenting a hybrid Active Contour Model (ACM) based on a Signed Pressure Force (SPF) function parameterized with a Kernel Difference (KD) operator. An SPF function includes information from both the local and global regions, making the proposed model independent of the initial contour position. The proposed model uses an optimal KD operator parameterized with weight coefficients to capture weak and blurred boundaries of inhomogeneous objects in images. Combined global and local image statistics were computed and added to the proposed energy function to increase the proposed model’s sensitivity. The segmentation time complexity of the proposed model was calculated and compared with previous state-of-the-art active contour methods. The results demonstrated the significant superiority of the proposed model over other methods. Furthermore, a quantitative analysis was performed using the mini-MIAS database. Despite the presence of complex inhomogeneity, the proposed model demonstrated the highest segmentation accuracy when compared to other methods.

The most fatal and frequent cancer amongst women is breast cancer. Mammography provides timely detection of lumps and masses in breast tissue, but effective diagnosis requires accurately identifying malignant tumor boundaries, which remains challenging, particularly for images with inhomogeneous regions. Therefore, we propose an active contour method based on a reformed combined local and global fitted function to address breast tumor segmentation. This combined function is strengthened by a proposed average energy driving function to capture obscure boundaries for regions of interest more precisely from inhomogeneous images. Including a p-Laplace term eliminates reinitialization requirements and suppresses false contours in the segmentation. Bias field signal, which causes image homogeneity corruption, is estimated by bias field initialization to ensure independence from the initial contour position. Local and global fitted models are incorporated by introducing bias fields within them. The proposed method was tested on the MIAS MiniMammographic Database, with quantitative analysis to calculate its accuracy, effectiveness, and efficiency. Experimentation confirmed the proposed method provided superior results compared with previous state-of-the-art methods.