Legal analytics recently is going through transformational journey with new machine learning models producing promising results. This paper is an attempt to predict outcomes of court judgments. The labeled encoded dataset was published with pre-trained embedding. Paper describe and experimentally compare multiple judgment classification techniques that use linear classifiers (logistic regression, SVMs), CNN and LSTM with word2vec and keras word embeddings. Experimental results are evaluated using standard matrices, show promising results (F1-score extending 0.8). It is shown that the sequence respecting approaches do better compared to Bag of word models. Further improvements were observed by using word embeddings.
The aim of this paper is to understand the dynamics and tools required to develop a software-based L4-L7 traffic generator. The main goal of this paper is to provide a simple, efficient and complete framework for fast packet processing in data plane applications. Conventional techniques of packet processing are rather slow, time-consuming and inefficient. Fast packet processing on the other hand, places substantial importance on eliminating these deficiencies. This paper places a special emphasis on explaining the essential functionalities and architectural details of T-Rex, along with a basic analysis of other tools available in the market, such as Pktgen, MoonGen and Ostinato. The above tools have been compared and tested for against various parameters. The essential question of finalizing an efficient tool for developing a traffic generator for L4L7 layers has thus been answered. The paper also strives to provide an insight into the methodology for implementing this work. In conclusion, the efficient tools have been spotted and the future stages of the work have been elucidated.
Sarees are integral to Indian culture and serve as daily attire for most women on the subcontinent. Despite their popularity, there exists a gap in research regarding the automatic segmentation of sarees and the independent color modification of distinct components. Existing methods rely on labor-intensive manual adjustments through commercial applications, impeding productivity and resulting in avoidable expenses. This paper presents a tool that smartly coordinates different deep-learning techniques to modify the color patterns found on different parts of a saree. MODNet is applied for background removal and custom-trained Mask R-CNN models are utilized to precisely segment the saree body and border. The subsequent application of a color-changing algorithm in the HSV color space facilitates independent color modification for the saree border and body. The methodology proposed in this paper can be extended to any kind of clothing such as shirts, trousers, kurtas, kimonos, etc. An accuracy of 93.01% was achieved for the saree border segmentation, and an accuracy of 89.23% was achieved for the saree body segmentation when tested on a set of 50 test images.